Study Plan

PhD students have to attend at least 140 hours of courses overall in 3 years (the earlier the better).
Each PhD student is expected to:
  • attend and take the exam of three or more courses involving at least 80 hours of lectures in total;
  • attend at least additional 60 hours of training activities without exam (or without taking the exam, if the course is with exam);
  • attend one PhD school organized by PhD-AI.it (the corresponding hours are included in the 60 hours above)
The additional 60 hours of training activities may include:
  • cycles of seminars and doctoral schools with specific indication that they are aimed exclusively or mainly at doctoral students;
  • (up to 20 hours) activities on soft skills, research management, European and international research systems, entrepreneurship, intellectual property, etc. See e.g., the PhD+ and CyB+ courses offered by the University of Pisa program Contamination Lab, and the cross-curricular educational activities  (open science, soft skills, etc.) offered at the University of Pisa.
The courses with exams and training activities without exams should be selected among the ones made available by:
  • our PhD program (see below) and by the other 4 PhD programs of PhD-AI.it (links to be added);
  • by the PhD program in Computer Science at the University of Pisa or by PhD programs at the host University.
  • by other Italian and International universities or research institutions (subject to approval).

The list of curses of the previous Academic Years are available: 2023-2024, 2022-2023, 2021-2022.

First year PhD students have to submit their study plan by 20th December.

To submit/update your study plan, please fill and sign this form, and send it to: secretariat-ai-society@phd-ai.it.

You can attend the courses freely. It may be useful for the lecturers to know the number of interested students. Thus, it would be kind of you to send an email to the lectures of courses included in your study plan to let them know that you intend to attend the course.

Certification of attendance/exam. After passing the exam (or attending the course, if it is without exam), please ask the lecture to fill and sign the attendance statement. Keep all statements in PDF with you. The statements will have to be attached at the yearly report you will submit for the yearly assessment in October.

Ph.D. Courses – Academic Year 2024-2025

3D Geometry Representation and Processing for Deep Learning

Institution: Consiglio Nazionale delle Ricerche
Location: Pisa – Department of Computer Science
Level: Ph.D. level
Type: Intermediate course
Attendance Mode: Blended
Exam: Yes
Lecturers: Paolo Cignoni, Massimiliano Corsini, Daniela Giorgi, Luigi Malomo
Email: paolo.cignoni@isti.cnr.it
Academic Year: 2024/2025
Semester: 2
Hours: 32
Timetable: https://sites.google.com/view/3d-geom-learning-2025/home
Abstract: Computer Graphics and Geometry Processing are the main disciplines dealing with 3D data such as meshes and point clouds. In turn, Artificial Intelligence and Deep Learning are fundamental paradigms to manage visual data. Nevertheless, applying traditional learning paradigms on 3D data requires rethinking architectural building blocks designed for 2D images.
In this course, we will introduce different representations for 3D data, and basic geometry processing techniques that intervene in deep learning pipelines (discrete differential geometry, sampling, remeshing, conversion, …). Then, we will introduce methods able to learn tasks on 3D data. We will describe different architectures to process complex geometric domains, and the novel mechanisms introduced in the literature to preserve by design their intrinsic properties. Examples include graph learning techniques, augmented with geometric and topological information; attention modules to process unordered point sets and mesh data; transformer-like architectures for unstructured data.
Learning based, radiance oriented approaches for 3D objects representation and rendering, (like NERF, Gaussian Splatting and variants) will be also introduced and discussed.
In the final part of the course, we will present different applications where the interplay between Computer Graphics/Geometry Processing and Deep Learning is opening up to exciting results, including Computational Fabrication, Assisted Design, Architectural Geometry, and Environmental Monitoring.
Syllabus: – 3D Data Representation
– Discrete Differential Geometry
– Differentiable Rendering
– Radiance based representations (NERF & Gaussian Splatting)
– ML for Geometric Representations
– Geometric Deep Learning
– Generative Models for 3D
Available for CircleU students: Yes

Advanced Laboratory of Complex Network Analysis

Institution: Università di Pisa, Consiglio Nazionale delle Ricerche
Location: University of Pisa, Largo Bruno Pontecorvo
Level: Master level
Type: Advanced course
Attendance Mode: In person
Exam: Yes
Lecturers: Giulio Rossetti, Barbara Guidi
Email: giulio.rossetti@isti.cnr.it, barbara.guidi@unipi.it
Academic Year: 2024/2025
Semester: 2
Hours: 48
Timetable: September-December 2025

Abstract: Delving deep into the intricacies of complex systems—be they social, biological, or technological—is vital for accurately modeling and effectively tackling the pressing issues that define our world today. Take, for instance, the need to diminish polarization and radicalization in online discussions, predict high-frequency financial transactions or understand the dynamic interactions among proteins.

This laboratory course aims to equip students with the tools to construct robust pipelines for analyzing complex systems derived from real-world data and represented as graphs. It will introduce key methodologies for data collection and preprocessing for graph analysis, delve into models designed to enhance the graph’s descriptive capabilities and practical applications and explore techniques for evaluating experimental outcomes. The course emphasizes hands-on learning, empowering students to gain practical insights into these concepts through the utilization of dedicated Python libraries.

Syllabus: Where to start: Formulating Hypotheses
Modeling Choices: From simple graphs to advanced models
Network Sampling
Data Collection: API & Web Scraping
Graph Transformation
Feature-rich modeling
How to Validate: check the statistical significance of network-based studies
Experiment reproducibility & Open Science
Available for CircleU students: No

Advanced Topics in Machine Learning

Institution: Scuola IMT Lucca
Location: Lucca, Piazza S. Francesco 19, IMT Lucca, Classroom to be chosen
Level: Ph.D. level
Type: Advanced course
Attendance Mode: Blended
Exam: Yes
Lecturers: Giorgio Stefano Gnecco
Email: giorgio.gnecco@imtlucca.it
Academic Year: 2024/2025
Semester: 2
Hours: 10
Timetable: June 2025
Abstract: The course provides an introduction to the theory behind some advanced machine learning techniques, including some topics of recent research. MATLAB implementations of most of the techniques examined in the course are described in the related course “MATLAB for Data Science”.
Syllabus: Lecture 1: Advanced treatment of principal component analysis and linear discriminant analysis.
Lecture 2: Convergence analysis of batch gradient descent and stochastic gradient descent.
Lecture 3: The perceptron learning algorithm. Backpropagation.
Lecture 4: Matrix completion and its application to recommendation systems.
Lecture 5: Network Lasso.
Available for CircleU students: Yes

AI Bearing with the AI Act, research exemptions and other traps: navigating legal and ethical dimensions

Institution: Scuola Superiore Sant’Anna
Location: Scuola Superiore Sant’Anna Piazza Martiri della libertà 33 Pisa
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: Yes
Lecturers: Prof. Giovanni Comandè
Email: g.comande@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 15
Timetable: Feb. 13 2025 1500-1800
Feb. 14 2025 0900-1200
Feb. 17 2025 1500-1800
Feb. 18 2025 0900-1200
Feb. 19 2025 0900-1200
Abstract: The course introduces the candidates to the key elements of the AI Act. It analyses the twists and thorns of the rules “in favor” of research and SME and casts regulation in the framework of compliance needs and ethical constraints.
Syllabus: Will be shared with students thaat enrol writing to the teacher
Available for CircleU students: Yes

AI Ethics Today

Institution: Università di Trento
Location: Trento (room to be defined)
Level: Ph.D. level
Type: Advanced course
Attendance Mode: In person
Exam: Yes
Lecturers: James Brusseau (Pace University, USA)
Email: iecs.school@unitn.it
Academic Year: 2024/2025
Semester: 1
Hours: 20
Timetable: https://iecs.unitn.it/node/1406
Abstract: 1. Through case studies and classroom discussion, we will develop the core principles of AI ethics and explore their application to today’s technology. We will learn to talk about the human side of AI innovation.
2. Consider the primary debates in the contemporary philosophy and ethics of artificial intelligence.
3. Students will be equipped to respond to ethics committees, and to produce AI ethics evaluations, sometimes referred to as AI ethics audits / algorithmic impact statements.
Syllabus: Program
1. Investigate the core principles employed in today’s AI ethics.
• Individual values: Autonomy, Human Dignity, Privacy
• Social values: Fairness, Equity, Sustainability/Social Wellbeing
• Technical values: Performance, Safety, Accountability
2. Apply the principles’ application in real cases, including AI healthcare applications, driverless cars, and similar.
A minimum of 75% attendance is required.Teaching methods
The teaching method is classroom discussion of case studies, and lectures presented by the professor. There are no required texts and no homework – but attendance at seminar sessions is required because the course’s main ideas will be developed collaboratively, through the seminar discussions. AI ethics will be learned by doing AI ethics.Assessment methods
Students will present a power point / poster presentation. It will be an AI ethics evaluation of an AI application. The AI application may be a tool the student is developing in their own work, or it may be a publicly known artificial intelligence application (ChatGPT, for example, or smart glasses, or Tesla and autopilot). The presentation will last 15 – 20 minutes plus 5 – 10 minutes of questions.
Students will be graded on their ability to locate the ethical dilemmas that arise around AI technology, and their ability to discuss the dilemmas knowledgeably. There are no right or wrong answers in ethics, but there are better and worse understandings of the human values that guide and justify decisions.
Because the main ideas will be developed through classroom discussion, attendance to at least 80% of seminar sessions is required in order to do the final presentation.Bibliography
The bibliography will be the seminar sessions and the subsequently published decks.
Website: https://trento.ai.ethicsworkshop.org/
Available for CircleU students:

An introduction to large language models

Institution: Università di Firenze
Location: School of Engineering, via di Santa Marta 3, Florence
Level: Ph.D. level
Type: Intermediate course
Attendance Mode: Blended
Exam: Yes
Lecturers: Marco Lippi
Email: marco.lippi@unifi.it
Academic Year: 2024/2025
Semester: 2
Hours: 12
Timetable: 21-23-28-30 January 2025
Abstract: This course will provide a general introduction to large language models, starting from background concepts in the area of natural language processing and providing key insights to specific topics related to pre-training, fine-tuning, prompt engineering, safety and security issues.
Syllabus: Background and general concepts from NLP: language models, transformers, attention. Pre-training. Prompt engineering: zero-shot, few-shot, chain-of-thought, and the like. Fine-tuning. Retrieval augmented generation. Tasks and performance evaluation. Limitations, safety and security issues.
Available for CircleU students:

Answer Set Programming – ASP

Institution: Università dell’Aquila
Location: https://univaq.webex.com/meet/stefania.costantini
Level: Ph.D. level
Type: Intermediate course
Attendance Mode: Online
Exam: Yes
Lecturers: Stefania Costantini
Email: stefania.costantini@univaq.it
Academic Year: 2024/2025
Semester: 2
Hours: 12
Timetable: Mondays 12:00-18:00
Abstract: The course provides an introduction to Answer Set Programming, a very succesful declarative programming paradigm, which is widely used for planning, logictics, configuration, games, with attention to both theory and practice. The course will be held only if at least four students will attend. The start date will be agreed upon with the students.
Syllabus: * Background on Logic
* ASP Intuition and Semantics
* ASP Applications
Available for CircleU students: Yes

Applied Econometrics: Policy Evaluation and Causality

Institution: Scuola IMT Lucca
Location: IMT-Lucca- Piazza San francesco
Level: Ph.D. level
Type: Advanced course
Attendance Mode: Blended
Exam: Yes
Lecturers: Francesco Serti
Email: francesco.serti@imtlucca.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: Beginning of June-beginning of July
Abstract: This module covers some of the most important methodological issues arising in any field of applied economics when the main scope of the analysis is to estimate causal effects. A variety of methods are illustrated using theory and papers drawn from the recent applied literature using econometric and machine learning tools.
Syllabus: 1 Causality, Randomized Experiments, and Directed Acyclic Graphs
a) Basic questions in empirical research
b) Rubin Causal model
c) Social Experiments
d) Directed Acyclic Graphs
e) Randomization Inference
2 Regression and Causality
a) Properties of the Conditional Expectation Function
b) Bad controls
c) Sources of bias
d) Conditional Independence Assumption
3 Instrumental variables (IVs)
a) Basics/recap
b) IVs and causality
c) IVs with heterogeneous treatment effects – LATE
d) Weak instruments
e) The bias of 2SLS
f) Popular IVs designs
4 Matching
a) Covariate Matching
b) Propensity Score Matching
c) (Augmented) Inverse Probability Weighting (AIPW)
d) Entropy balancing
e) Regression adjustment
5 Differences-in-Differences
a) Basics/recap
b) Regression Differences-in-Differences
c) Robustness checks and picking a suitable control group
d) DiD with heterogeneous treatment effects and staggered policy adoption.
6 Regression Discontinuity Design
a) Sharp RD
b) Fuzzy RD
c) Continuity-based and local-randomization approaches
d) Parametric vs. non-parametric approaches
7 The Synthetic Control Method (SCM)
a) Basics
b) Extrapolation and interpolation biases
c) Multiple treated units
d) Placebos, robustness checks, and inference
8 Causal Machine Learning (ML)
a) ML tools for Partial linear regression, AIPW, IV-LATE, DiD, SCM
b) ML to build counterfactuals when no control group is available
c) ML to study heterogeneity of treatment effects
d) Policy Learning
BibliographyReferences to relevant research papers and books will be provided during the lectures. Lecture slides will be regularly distributed to the students.Teaching MethodAfter reviewing the theory behind each empirical method, we focus on their practical implementation by analyzing some examples from the applied economic literature.Final exam (elective)The assessment is based on producing a short empirical project using one of the methods studied in class.

Available for CircleU students: Yes

Applied Statistical Modelling 1

Institution: Scuola Superiore Sant’Anna
Location: Sant’Anna School
Level: Ph.D. level
Type: Intermediate course
Attendance Mode: In person
Exam: Yes
Lecturers: Chiara Seghieri
Email: chiara.seghieri@santannapisa.it
Academic Year: 2024/2025
Semester: 1
Hours: 20
Timetable: Nov-Dec 2024
Abstract: The course aims at providing students with methodological and applied background on statistical models for analysing data with different types of response variables. The course provides a practice-oriented approach with applications in the context of social sciences and practical examples using R software. The course focuses on: linear regression, generalized linear models for binary, ordinal and count responses, multilevel models.
The course assumes prior knowledge of foundations of Probability and Inferential Statistics (point estimates, confidence intervals and hypothesis testing).
Syllabus: Introduction to the course and to linear regression
Linear regression:model diagnostics, multiple linear regression
GLM introduction, logit model
Probit model, ordinal logit and probit
Poisson regression and other GLMs
Random effect models
Recap and applications
Available for CircleU students: No

Applied Statistical Modelling 2

Institution: Scuola Superiore Sant’Anna
Location: Scuola Superiore Sant’Anna Pisa
Level: Ph.D. level
Type: Intermediate course
Attendance Mode: In person
Exam: Yes
Lecturers: Valentina Lorenzoni
Email: valentina.lorenzoni@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 10
Timetable: to be defined, approximately on March/April
Abstract: The course aims to provide students with methodological and applied background of model for time-to-event data, focusing on survival analysis and specifically on Cox proportional hazard model and on model for competing risk. The course provide a practice-oriented approach with applications in the context of social sciences.
The course assumes prior knowledge of foundations of Probability, Inferential Statistics and Regression models
Syllabus: Intro to time-to-event data; Life tables; Main statistical methods for survival analysis
Available for CircleU students:

Bioinformatics

Institution: Scuola Normale Superiore
Location: Scuola Normale Superiore, Piazza dei Cavalieri 7, Pisa
Level: Ph.D. level
Type: Intermediate course
Attendance Mode: Blended
Exam: Yes
Lecturers: Francesco Raimondi, post-docs of the Bioinformatics group
Email: francesco.raimondi@sns.it
Academic Year: 2024/2025
Semester: 2
Hours: 40
Timetable: From end of January to end of April
Abstract: Aim of the course is to provide students with the basic
knowledge of bioinformatics techniques as an easy and
friendly support for their study and research careers. This
will entail: 1) theory of the most common bioinformatics
algorithms and resources: who they are, what they do
and why they are so important and increasingly used in
modern biology research; 2) basic practical experience
through hands-on-sessions on typical problems that can
be answered by using popular online tools.
Syllabus: 1) Introduction to bioinformatics
2) Biological databases
3) Pairwise sequence alignments
4) Basic Local Alignment Search Tool (BLAST)
5) Multiple sequence Alignment
6) Protein analysis and Proteomics
7) Introduction to Protein structure
8) Homology Modeling
9) Fold recognition
Available for CircleU students: Yes

Biostatistics

Institution: Scuola Superiore Sant’Anna
Location: Pisa, Scuola Superiore Sant’Anna
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: In person
Exam: Yes
Lecturers: Valentina Lorenzoni
Email: valentina.lorenzoni@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 16
Timetable: To be defined, approximately from february/march
Abstract: The course offers an introduction into main concept and measures used in epidemiology and offers a snapshot of main statistical methods for the analysis of epidemiological and clinical data. The course will consist of both theoric and applied classes to let students familiarize with biostatistical methods and with practical problems in the analysis of real data. The course will also provide cues for a correct use of methods, interpretation and critical appraisal of analyses.
Syllabus: Introduction to epidemiology; Relation and agreement; Linear regression; Logistic regression; Dealing with collinearity, confounding and interaction; Survival analysis
Available for CircleU students:

Causal Inference

Institution: Università di Firenze
Location: Viale Morgagni, 59. 50134 – Florence
Level: Ph.D. level
Type: Intermediate course
Attendance Mode: In person
Exam: No
Lecturers: Marco Doretti, Alessandra Mattei
Email: marco.doretti@unifi.it and alessandra.mattei@unifi.it
Academic Year: 2024/2025
Semester: 2
Hours: 24
Timetable: June / July 2025
Abstract: The aim of the course is to provide students with the basic concepts of Causal Inference, framed with the formal language of Potential Outcomes as well as via the graphical approach. A range of methods will be introduced which allow to identify and estimate casual effects not only in the presence of randomized experiments, but also by means of observational data. Such methods include covariate adjustment, difference-in-differences, synthetic control, causal inference methods with time series and instrumental variable techniques; the assumptions underlying each of them will be discussed. We will also show how similar issues are addressed, though with a different terminology, in many applied disciplines (like Epidemiology and Demography) as well as in the literature dealing with performance evaluation. Further topics touched in the course concern Mediation Analysis and Principal Stratification.
Syllabus: Introduction to the potential outcome approach; Design and analysis of randomized studies; Design and analysis of observational studies under unconfoundedness; Causal inference with panel data and times series: DiD methods, synthetic control methods, causal inference methods with time series; Causal inference in irregular designs: IV methods, Principal Stratification; Mediation Analysis.
Available for CircleU students:

Causal Inference in Macroeconometrics

Institution: Scuola Superiore Sant’Anna
Location: Sant’Anna School, Piazza Martiri della Libertà 33, Pisa.
Level: Ph.D. level
Type: Advanced course
Attendance Mode: In person
Exam: No
Lecturers: Alessio Moneta
Email: a.moneta@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 12
Timetable: May 8th, 15th, 22nd, 29th, June 5th 2025, Sant’Anna School.
Abstract: The course aims at addressing the problem of identifying and quantifying causal relationships in macroeconomics. The course will deliver an overview of methods that allow researcher to estimate causal effects from time-series data in a non-experimental setting.
Syllabus:
– A Historical Perspective on Causal Inference in Macroeconometrics
– The Structural Vector Autoregressive Model: Identification Strategies- Causal Inference by Graphical Causal Models (an Introduction)- Causal Inference by Independent Component Analysis
Available for CircleU students:

Cloud Computing & Big-Data

Institution: Scuola Superiore Sant’Anna
Location: Students should contact the lecturer, and they will receive instructions to attend and/or connect via e-mail
Level: Ph.D. level
Type: Intermediate course
Attendance Mode: Blended
Exam: Yes
Lecturers: Prof. Tommaso Cucinotta, Scuola Superiore Sant’Anna
Email: tommaso.cucinotta@santannapisa.it
Academic Year: 2024/2025
Semester: 1
Hours: 30
Timetable: To be decided. The course will be held in the period November – January. More information is available at: https://retis.sssup.it/~tommaso/eng/courses/CloudComputingBigData.html
Abstract: This course provides an overview of the challenges to face, and the technical solutions to embrace, when building large-scale, fault-tolerant, distributed and replicated real-time cloud services. These systems need to be capable of serving millions/billions of requests per second with industrial-grade reliability, availability and performance, and are composed of thousands of components spanning across millions of machines, worldwide. The course focuses on design, development and operations of scalable software systems, including big-data processing and analytics, as used increasingly often for nowadays intensive computations needed to train large machine-learning and artificial intelligence models, where the huge volumes of data to handle mandates the use of heavily distributed algorithms. The course covers also basic concepts on networking architectures for data-centre and cloud computing infrastructures.
Syllabus: -) Cloud Computing
* Basic concepts
* Scalability and elasticity in cloud systems
* Fault-tolerance and replication
* Real-time cloud services
* Operations and devops engineering
-) Big Data and Analytics
* Basic concepts
* Real-time data streaming and analytics
* Distributed file-system
* SQL vs NoSQL data-base systems
* Big-Data and the Internet of Things
-) Platforms
* Overview of public cloud services (AWS EC2, Google GCP, …)
* Apache Hadoop, Storm, Spark
* Map Reduce
* OpenStack
Available for CircleU students: Yes

Cloud Computing & Big-Data Lab

Institution: Scuola Superiore Sant’Anna
Location: Students need to contact the lecturer, who will send them by e-mail attendence and/or connection instructions
Level: Ph.D. level
Type: Advanced course
Attendance Mode: Blended
Exam: Yes
Lecturers: Prof. Tommaso Cucinotta, Scuola Superiore Sant’Anna
Email: tommaso.cucinotta@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 30
Timetable: To be decided. The course will be held in the period May – July. More information is available at: http://retis.santannapisa.it/~tommaso/courses/CloudComputingBigDataLab.php
Abstract: This is a hands-on and applied course following up on the Cloud Computing & Big-Data course. Here, students will put in practice the theoretical/abstract concepts acquired in the general course on Cloud Computing & Big-Data. During the practical sessions, we’ll have a deep dive on such concepts as: machine virtualization and OS-level virtualization on Linux; virtual networking on Linux; programming abstractions for cloud and distributed computing; elasticity in practice; big-data programming frameworks; command-line interface for major public cloud services; popular open-source cloud platforms.
Syllabus: -) Virtualization Fundamentals
* KVM Command-Line Interface
* libvirt and virtual-manager
-) Virtual Switching on Linux
* brctl and OpenVSwitch
-) Containers
* LXC and netns
-) Public Cloud Services
* AWS EC2, CloudWatch
* AWS S3, DynamoDB
-) Open-source cloud platforms
* OpenStack Nova, Glance, Neutron
* OpenStack Heat/Senlin, Ceilometer/Monasca
* Kubernetes
-) Platforms for Big Data and Analytics
* Map Reduce
* Apache Spark
Available for CircleU students: Yes

Complexity in ecology

Institution: Scuola IMT Lucca
Location: IMT School for Advanced Studies Lucca (classroom and online link to be confirmed)
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: No
Lecturers: Andrea Perna
Email: andrea.perna@imtlucca.it
Academic Year: 2024/2025
Semester: 2
Hours: 10
Timetable: September 2024 (tentatively: 9th, 11th, 16th, 18th, 23rd between 11am and 1pm)
Abstract: This short module is designed to provide a basic understanding of the way how ecological systems self-assemble and function, and of the mathematical and computational tools that can be used to characterise these systems.
Syllabus: * Patterns at the individual level: scaling of ontogenetic growth, movement and metabolism.
* Patterns at the level of groups and populations: group-size distribution, collective behaviour.
* Patterns at the level of ecological communities and ecological interactions (size-abundance distribution, ecological networks).
* Ecosystem-level patterns: diversity and productivity, geographic variation.
* Ecosystems through change: multiple stable states and ecological transitions.
Available for CircleU students: Yes

Computational Economics

Institution: Scuola Superiore Sant’Anna
Location: Scuola Superiore Sant’Anna
Level: Post graduate Master level
Type: Introductory course (no or few prerequisites)
Attendance Mode: In person
Exam: Yes
Lecturers: Giorgio Fagiolo, Andrea Roventini, Andrea Vandin
Email: giorgio.fagiolo@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 56
Timetable: March-May 2025
Abstract: This course is intended to serve as a broad introduction to the huge literature using agent-based computational approaches to the study of economic dynamics. It is organized in three parts. The first one (“Why?”) will discuss the roots of the critiques to the mainstream paradigm from a methodological, empirical and experimental perspective. We shall briefly review the building blocks of mainstream models (rationality, equilibrium, interactions, etc.) and shortly present some of the evidence coming from cognitive psychology and experimental economics, network theory and empirical studies, supporting the idea that bounded rationality, non-trivial interactions, non-equilibrium dynamics, heterogeneity, etc. are irreducible features of modern economies. In the second part (“What?”) we shall discuss what ACE is and what are its main tools of analysis. We will define an ABM and present many examples of classes of ABMS, from the simplest (cellular automata, evolutionary games) to the most complicated ones (micro-founded macro models).The third part (“How?”) aims at understanding how ABMs can be designed, implemented and statistically analyzed. The course also contains an introduction to programming in Python (Andrea Vandin) and applications of agent-based models to macroeconomics (Andrea Roventini).
Syllabus: Introduction to programming in Python; agent-based computational economics (why? what? how?); applications of agent-based models to macroeconomics.
Available for CircleU students:

Computational fluid dynamics

Institution: Scuola Superiore Sant’Anna
Location: Sant’Anna Pisa sede centrale
Level: Master level
Type: Intermediate course
Attendance Mode: Blended
Exam: Yes
Lecturers: Giovanni Stabile
Email: giovanni.stabile@santannapisa.it
Academic Year: 2024/2025
Semester: 1
Hours: 20
Timetable: Started mid of ofctober (classes are recorded)
Abstract: The course deals with a list of advanced topics in computational fluid dynamics. In the first part, the governing equations governing fluid dynamics problems are reviewed and derived. Both compressible and incompressible flows are considered. The basics of the finite volume methods for the numerical discretization of fluid dynamics problems are reviewed and discussed starting from the basic example of an advection-diffusion equation. Particular emphasis is given to the treatment of non-orthogonality, convection-dominated flows, time discretization, and order of accuracy. Numerical schemes for the treatment of velocity pressure coupling for the incompressible Navier-Stokes equation such as the SIMPLE and the PISO algorithms are reviewed and a discussion on chequerboard effects on collocated grids is provided. The last part of the course focuses on advanced topics related to turbulent and compressible flows. The various alternatives (RANS, LES) for turbulence modeling are introduced and discussed in detail. Finally, an introduction to numerical methods for compressible flows is provided.
Syllabus: no syllabus
Available for CircleU students: Yes

Computing Methods for Experimental Physics and Data Analysis

Institution: Università di Pisa
Location: Polo Fibonacci, University of Pisa
Level: Master level
Type: Advanced course
Attendance Mode: In person
Exam: Yes
Lecturers: Andrea Rizzi, Alessandra Retico
Email: andrea.rizzi@unipi.it, alessandra.retico@pi.infn.it
Academic Year: 2024/2025
Semester: 1
Hours: 40
Timetable: November – December 2024 (Monday 16:30-18:30; Tuesday 8:30-11:30)
Abstract: The course for PhD students is part of a more extensive MSc course. The latter includes lectures dedicated to best practice in code development with a focus on scientific collaboration, python programming, principles of parallel computing. The lectures for PhD students are focused on: the design of neural networks for scientific data analysis; the development of analysis projects in the context of particle physics or medical physics.
Syllabus: By the end of the course the student will know the following tools for scientific computing and data analysis:
– tools for machine learning and artificial neural network development
– specific data analysis tools for particles physics or medical physics
Available for CircleU students:

Cycle of Seminars for PhD students on Artificial Intelligence

Institution: Università di Pisa
Location: Dipartimento di Informatica, Università di Pisa, Largo B. Pontecorvo 3, 56125 Pisa, Italy
Level: Ph.D. level
Type: Cycle of seminars
Attendance Mode: Blended
Exam: No
Lecturers: Main contact: Salvatore Ruggieri
Email: salvatore.ruggieri@unipi.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: Once or twice a week in the period February to May 2025
Abstract: The aim is to introduce new PhD students to topics that arise in the life of a researcher in AI, including how to search for knowledge and state-of-the-art, how to access computational resources, how to write a scientific paper, how to make an effective presentation in public, how to measure the performance of scientific publications, how to disseminate research, how to collaborate in scientific projects, etc. The seminars will be given by speakers with a specific background on the topic of the seminar.
Syllabus: The list of seminars will be released in January 2025.
Available for CircleU students: Yes

Data Driven Engineering

Institution: Scuola Superiore Sant’Anna
Location: Scuola Superiore Sant’Anna Pisa
Level: Ph.D. level
Type: Advanced course
Attendance Mode: Blended
Exam: Yes
Lecturers: Giovanni Stabile
Email: giovanni.stabile@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: March – May
Abstract: The course deals with the main tools to perform dimensionality reduction and data-driven approximation of engineering problems. Both linear (proper orthogonal decomposition) and nonlinear approaches (autoenconders) will be reviewed in relation to dimensionality reduction. The main aspects of defining and designing experiments to implement a data-driven surrogate model will be reviewed. The main techniques discussed are the dynamic mode decomposition, the proper orthogonal decomposition with interpolation, neural networks, and Gaussian progress regression. The methodology is demonstrated using Python examples in Colab.
Syllabus: no syllabus
Available for CircleU students: Yes

Dynamic Factor Models

Institution: Scuola Superiore Sant’Anna
Location: Piazza Martiri delle Libertà, 33 Pisa
Level: Ph.D. level
Type: Advanced course
Attendance Mode: In person
Exam: Yes
Lecturers: Matteo Barigozzi
Email: laura.magazzini@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 7
Timetable: 18/2/2024 and 19/2/2024
Abstract: The analysis of high-dimensional time series has become one of the most active subjects of modern statistical methodology. To achieve dimension reduction, several new analytical and computational techniques have been developed under the name of machine learning methods. Among these factor models not only are one of the pioneering methods in the field of unsupervised learning (dating back to Spearman, 1904), but up to these days have also been one of the most popular and most employed ones. The aim of this course is to provide an introduction to factor models in time series analysis by teaching students the basic theoretical foundations and by illustrating them some applications to econometric analysis (knownledge of time series analysis is required).
Syllabus: History and Taxonomy.
Representation and identification.
Principal component analysis.
Quasi maximum likelihood.
Expectation Maximization algorithm
Dynamic principal component analysis.
Determining the number of factors.
Impulse response analysis and counterfactuals.
Coincident indicators.
Nowcasting and forecasting.
The case of cointegrated factors.
Available for CircleU students:

Elements of statistical inference and probabilistic models of cognition

Institution: Scuola IMT Lucca
Location: IMT School Lucca. Piazza San Francesco, 19. 55100 Lucca
Level: Ph.D. level
Type: Intermediate course
Attendance Mode: In person
Exam: Yes
Lecturers: Miguel Ibanez
Email: miguel.ibanezberganza@imtlucca.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: 20 maggio 2024 — 22 luglio 2024
Abstract: A gentle, non-rigorous overview of some topics in statistical inference, often from the point of view of statistical physics, and with a background motivational interest in probabilistic approaches to cognitive science.
Syllabus: – Motivational, introductory notions of probabilistic approaches to cognition. Bayesian estimators. Notions on unsupervised neural network learning. Expectation-Maximisation learning. Elements of Bayesian model selection. The Bayesian Information Criterion. Worked examples of model selection. Dimensionality reduction in Principal Component Analysis. Model selection and clustering. Latent Dirichlet Allocation. Variational inference. The Evidence Lower BOund approximation in ANN learning. The Hierarchical Gaussian Filter. Notions of probabilistic models of cognition.
Available for CircleU students:

Elements of statistical physics and statistical inference

Institution: Scuola IMT Lucca
Location: IMT School Lucca. Piazza San Francesco, 19. 55100 Lucca
Level: Ph.D. level
Type: Intermediate course
Attendance Mode: In person
Exam: Yes
Lecturers: Miguel Ibanez
Email: miguel.ibanezberganza@imtlucca.it
Academic Year: 2024/2025
Semester: 2
Hours: 15
Timetable: 24 febbraio 2024 — 2 aprile 2024
Abstract:
A gentle, non-rigorous introduction to some notions of statistical inference and information theory, adopting the perspective of statistical physics.
Syllabus:
– Statistical ensembles and emergence. Elements of equilibrium and non-equilibrium statistical physics. Sampling and inferring. The Markov Chain Monte Carlo method. Correlations, cumulants, partial correlations, and interactions. The Gaussian and Ising models. [Elements of stochastic processes on graphs.] The inverse problem: Bayesian estimators. Maximum entropy. Examples of maximum likelihood inference (with applications to biology and neuroscience). [Elements of Bayesian model selection. Dimensionality reduction in PCA.] Elements of random matrix ensembles. Inferring correlation and precision matrices. Elements of information theory. Information, entropy, and relevance.
Available for CircleU students:

Epistemic Logic Programming (ELP)

Institution: Università dell’Aquila
Location: https://univaq.webex.com/meet/stefania.costantini
Level: Ph.D. level
Type: Advanced course
Attendance Mode: Online
Exam: Yes
Lecturers: Stefania Costantini
Email: stefania.costantini@univaq.it
Academic Year: 2024/2025
Semester: 2
Hours: 12
Timetable: Lectures on Monday 14:00-18:00, start after the course on ASP, agreed with the students
Abstract: The course deals with Epistemic Logic Programming (ELP), a declarative programming paradigm which enriches ASP with operators of knowledge (K) and possibility (M). This allows a programmer to talk, within the program, about the consequences of the program itself. This allows for kinds of reasoning similar to what done in modal logic, within a decidable and reasonably complex setting.
Syllabus: * Short background on Logic and ASP, Motivation for ELPs
* ELPs Semantics
* ELPs New Semantics and Properties
Available for CircleU students: Yes

Evolutionary game Theory

Institution: Scuola IMT Lucca
Location: Piazza San Francesco 19, Lucca
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: No
Lecturers: Ennio Bilancini
Email: phd@imtlucca.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: 1 Apr 2025, Tue
9 – 11am
[first] BILANCINI – Evolutionary game theory
4 Apr 2025, Fri
9 – 11am
BILANCINI – Evolutionary game theory8 Apr 2025, Tue
2 – 4pm
BILANCINI – Evolutionary game theory
Ex-Boccherini-PT-Meeting Room (13)11 Apr 2025, Fri
9 – 11am
BILANCINI – Evolutionary game theory
CAMPUS San Francesco-PT-classroom 2 (24)15 Apr 2025, Tue
2 – 4pm
BILANCINI – Evolutionary game theory17 Apr 2025, Thu
9 – 11am
BILANCINI – Evolutionary game theory22 Apr 2025, Tue
11am – 1pm
BILANCINI – Evolutionary game theory

24 Apr 2025, Thu
9 – 11am
BILANCINI – Evolutionary game theory

29 Apr 2025, Tue
9 – 11am
BILANCINI – Evolutionary game theory

Abstract: Evolutionary methods allow to study how behaviors and traits evolve in a population of interacting agents. The object of evolution can be a biological or cultural trait or a profile of strategies in a game. The process by which it changes can depend on fitness, imitation or optimization, possibly as the outcome of a deliberative process.
Syllabus: Learning Outcomes:
To provide students with a state of the art overview of evolutionary game theory which can be useful to the potential researcher in the area as well as the interested scholar who works in a related field (behavioral sciences, social sciences, complexity studies).
Lecture Contents:
1. Overview of Evolutionary Game Theory
Basic concepts, techniques and findings, from ESS strategies to evolutionary stability.
2. Deterministic evolutionary dynamics
Models of deterministic evolution, mostly based on replicator dynamics and imitation.
3. Stochastic evolutionary models
Models of stochastic evolution, mostly based on markov chains. Equilibrium selection based on stochastic stability techniques.References:
Sandholm, William H. Population games and evolutionary dynamics. MIT press, (2010).
Newton, Jonathan. “Evolutionary game theory: A renaissance.” Games 9.2 (2018): 31.
Young, H. Peyton. Individual strategy and social structure: An evolutionary theory of institutions. Princeton University Press, (2001)
Available for CircleU students: Yes

Explainable Artificial Intelligence

Institution: Scuola Normale Superiore
Location: Scuola Normale Superiore, Palazzo della Carovana
Level: Ph.D. level
Type: Advanced course
Attendance Mode: Blended
Exam: Yes
Lecturers: Prof. Fosca Giannotti (Instructor), Dr. Roberto Pellungrini, Dr. Gizem Gezici (Teaching Assistants)
Email: fosca.giannotti@sns.it, roberto.pellungrini@sns.it, gizem.gezici@sns.it
Academic Year: 2024/2025
Semester: 2
Hours: 30
Timetable: https://docs.google.com/document/d/1JMqjewyvGmcfjZd9l0get0pXep6QSCzX/edit?usp=sharing&ouid=110852127181441456126&rtpof=true&sd=true
Abstract: Black box AI systems for automated decision making, often based on machine learning over (big) data, map a user’s features into a class or a score without exposing the reasons why. This is problematic not only for the lack of transparency, but also for possible biases inherited by the algorithms from human prejudices and collection artifacts hidden in the training data, which may lead to unfair or wrong decisions. The future of AI lies in enabling people to collaborate with machines to solve complex problems. Like any efficient collaboration, this requires good communication, trust, clarity and understanding. Explainable AI addresses such challenges and for years different AI communities have studied such topic, leading to different definitions, evaluation protocols, motivations, and results.
This (30 hours) course provides a reasoned introduction to the work of Explainable AI (XAI) to date, and surveys the literature with a focus on post-hoc and by-design approaches. We motivate the needs of XAI in real-world and large-scale application, while presenting state-of-the-art techniques and best practices, as well as discussing the many open challenges. An XAI platform with collection of many of the recently proposed algorithms will be presented on specific use cases and it will be possible familiarize with some of the methods.
The course is organized as follows in three modules: i) an introductory one providing motivations, main concepts and main methods; ii) an advanced one where the students will actively participate to monographs topics with readings interleaved with interventions of international scholars working on the sector; iii) an hands-on module where the students will be introduced to the usage on XAI methods.
Syllabus: https://docs.google.com/document/d/1JMqjewyvGmcfjZd9l0get0pXep6QSCzX/edit?usp=sharing&ouid=110852127181441456126&rtpof=true&sd=true
Available for CircleU students: No

Foundation of probability and statistical inference

Institution: Scuola IMT Lucca
Location: Lucca, Piazza San Francesco
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: No
Lecturers: Irene Crimaldi
Email: phd@imtlucca.it
Academic Year: 2024/2025
Semester: 1
Hours: 30
Timetable: November, 20 – December, 20
Abstract: This course covers the fundamental concepts of probability theory and statistical inference.
Some proofs are sketched or omitted in order to have more time for examples, applications
and exercises.
Syllabus: This course deals with the following topics:
– probability space, random variable, expectation, variance, cumulative distribution function,
discrete and absolutely continuous distributions,
– random vector, joint and marginal distributions, joint cumulative distribution function,
covariance,
– conditional probability, independent events, independent random variables, conditional
probability density function, order statistics,
– multivariate Gaussian distribution, copula functions,
– types of convergence and some related important results,
– Mathematical Statistics (point estimation, interval estimation, hypothesis testing, introduction
to Bayesian statistics).
Available for CircleU students: Yes

Game Theory

Institution: Scuola IMT Lucca
Location: Piazza San Francesco 19, Lucca
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: No
Lecturers: Ennio Bilancini
Email: phd@imtlucca.it
Academic Year: 2024/2025
Semester: 1, 2
Hours: 20
Timetable: 13 Feb 2025, Thu
9 – 11am
[first] BILANCINI – Game theory
CAMPUS San Francesco-PT-classroom 1 (24)
14 Feb 2025, Fri
9 – 11am
BILANCINI – Game theory
CAMPUS San Francesco-PT-classroom 1 (24)17 Feb 2025, Mon
2 – 4pm
BILANCINI – Game theory
CAMPUS San Francesco-PT-sacrestia (30)20 Feb 2025, Thu
9 – 11am
BILANCINI – Game theory
Ex-Boccherini-PT-Meeting Room (13)25 Feb 2025, Tue
11am – 1pm
BILANCINI – Game theory
CAMPUS San Francesco-PT-classroom 1 (24)27 Feb 2025, Thu
9 – 11am
BILANCINI – Game theory
CAMPUS San Francesco-PT-classroom 1 (24)4 Mar 2025, Tue
11am – 1pm
BILANCINI – Game theory
CAMPUS San Francesco-PT-sala della botte (14)

6 Mar 2025, Thu
11am – 1pm
BILANCINI – Game theory
CAMPUS San Francesco-PT-classroom 1 (24)

11 Mar 2025, Tue
11am – 1pm
BILANCINI – Game theory
CAMPUS San Francesco-PT-classroom 2 (24)

13 Mar 2025, Thu
11am – 1pm CAMPUS San Francesco-PT-sacrestia (30)

Abstract: The course provides a detailed discussion of state of the art in the modeling of interactive decision-making as games. Special attention will be given to the prediction of outcomes in strategic situations. For this purpose, prominent solution concepts of games are reviewed and discussed, together with their main refinements based on rationality and information requirements.

 

Syllabus: Learning Outcomes:
The goal is to equip students with an in-depth understanding of the main concepts and tools of game theory in order to enable them to successfully pursue research related to the analysis of strategic behavior and interactive decision-making.
Lecture Contents:
Game concepts covered: normal form game, extensive form game, strategy, mixed strategy, Dominance and iterative dominance, rationalizability, Nash equilibrium, subgame perfect Nash equilibrium, trembling hand perfect Nash equilibrium, weak perfect Bayes-Nash equilibrium, sequential equilibrium, perfect Bayes-Nash equilibrium, out-of-equilibrium beliefs refinements.
The discussion of all theoretical concepts will be accompanied by representative applications from biological, economic, information and social sciences.References:
Mas-Colell A, Whinston MD, Green JR. Microeconomic theory. New York: Oxford university press (chapters 7,8,9).
Available for CircleU students: Yes

Geospatial Analytics

Institution: Università di Pisa, Consiglio Nazionale delle Ricerche, Scuola Normale Superiore
Location: Largo Bruno Pontecorvo, 3, 56127 Pisa. Rooms L1 and C1
Level: Master level
Type: Introductory course (no or few prerequisites)
Attendance Mode: In person
Exam: Yes
Lecturers: Luca Pappalardo, Mirco Nanni
Email: mirco.nanni@isti.cnr.it
Academic Year: 2024/2025
Semester: 1
Hours: 40
Timetable: http://didawiki.di.unipi.it/doku.php/geospatialanalytics/gsa/start
Abstract: The analysis of geographic information, such as those describing human movements, is crucial due to its impact on several aspects of our society, such as disease spreading (e.g., the COVID-19 pandemic), urban planning, well-being, pollution, and more. This course will teach the fundamental concepts and techniques underlying the analysis of geographic and mobility data, presenting data sources (e.g., mobile phone records, GPS traces, geotagged social media posts), data preprocessing techniques, statistical patterns, predicting and generative algorithms, and real-world applications (e.g., diffusion of epidemics, socio-demographics, link prediction in social networks). The course will also provide a practical perspective through the use of advanced geoanalytics Python libraries.

Syllabus: Module 1: Spatial and Mobility Data Analysis

Fundamentals of Geographical Information Systems
Geographic coordinates systems
Vector data model
Trajectories
Spatial Tessellations
Flows
Practice: Python packages for geospatial analysis (Shapely, GeoPandas, folium, scikit-mobility)
Digital spatial and mobility data
Mobile Phone Data
GPS data
Social media data
Other data (POIs, Road Networks, etc.)
Practice: reading and exploring spatial and mobility datasets in Python
Preprocessing mobility data
filtering compression
stop detection
trajectory segmentation
trajectory similarity and clustering
Practice: data preprocessing with scikit-mobility

Module 2: Mobility Patterns and Laws

individual mobility laws/patterns
collective mobility laws/patterns
Practice: analyze mobility data with Python

Module 3: Predictive and Generative Models

Prediction
Next-location prediction
Crowd flow prediction
Spatial interpolation
Generation
Trajectory generation
Flow generation
Practice: mobility prediction and generation in Python

Module 4: Applications

Urban segregation models
Routing and navigation apps
Traffic simulation with SUMO

 

Available for CircleU students:

Intelligent Systems for Pattern Recognition

Institution: Università di Pisa
Location: Polo Fibonacci, L.go Bruno Pontecorvo 3, 56127 Pisa
Level: Master level
Type: Intermediate course
Attendance Mode: Blended
Exam: Yes
Lecturers: Davide Bacciu
Email: davide.bacciu@unipi.it
Academic Year: 2024/2025
Semester: 2
Hours: 72
Timetable: https://didattica.di.unipi.it/en/master-programme-in-computer-science/timetable-master-computer-science/
Abstract: The course introduces students to the analysis and design of advanced machine learning models for modern pattern recognition problems and discusses how to realize advanced applications exploiting computational intelligence techniques.
The course is articulated in four parts. The first part introduces basic concepts and algorithms concerning pattern recognition, in particular as pertains sequence and image analysis. The next two parts introduce advanced models from two major learning paradigms, that are (deep) neural networks and generative models, and their use in pattern recognition applications. The last part will go into the details of the realization of selected recent applications of AI models. Presentation of the theoretical models and associated algorithms will be complemented by introductory classes on the most popular software libraries used to implement them.
The course hosts guest seminars by national and international researchers working on the field as well as by companies that are engaged in the development of advanced applications using machine learning models.
Topics covered – Bayesian learning, graphical models, deep learning models and paradigms, deep learning for machine vision and signal processing, advanced neural network models (recurrent, recursive, etc.), (deep) reinforcement learning, signal processing and time-series analysis, image processing, filters and visual feature detectors, pattern recognition applications (machine vision, bio-informatics, robotics, medical imaging, etc), introduction to machine learning and deep learning libraries.
Syllabus: https://elearning.di.unipi.it/course/view.php?id=278
Available for CircleU students: No

Introduction to energy and resources economics

Institution: Scuola IMT Lucca
Location: IMT School for Advanced Studies Lucca, Piazza S. Francesco 19, 55100 Lucca
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: No
Lecturers: Angelo Facchini
Email: angelo.facchini
Academic Year: 2024/2025
Semester: 2
Hours: 12
Timetable: 17-02-2025 to 24-02-2025
Abstract: The course provides a first understanding of resource management and energy economics. The student will become familiar with the basic concepts of resources and energy economics, including the taxonomy of resources, the Hartwick and the Hotelling rules. The second part of the course focuses on energy and electricity, exploring the market mechanisms and the main liberalisation reforms that occurred in Italy.
Syllabus: The course is organised in the following lectures:
1) Basic resource Management
2) Introduction to Energy
3) The transition to Renewable Energy Sources
4) Electricity transmission, distribution and markets
5) The liberalization of electricity markets: the Italian way
Available for CircleU students: Yes

Introduction to Life Cycle Assessment

Institution: Scuola IMT Lucca
Location: IMT School for Advanced Studies, Piazza S. Francesco 19, 55100 Lucca
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: No
Lecturers: angelo Facchini
Email: angelo.facchini@imtlucca.it
Academic Year: 2024/2025
Semester: 1
Hours: 20
Timetable: 3-03-2025 to 24-03-2025
Abstract: The course aims to introduce the Life Cycle Assessment to evaluate environmental impact. The student will become familiar with the LCa and other material flow accounting methods. In the first part of the course, the student will become familiar with the basic concepts of MFA and LCA. During the second part, the lectures will focus on using common LCA software to implement case studies of increasing complexity.
Syllabus: The course is organised in two parts. The first part is composed by the following lectures:
1) Introduction and principles of sustainability
2) Environmental accounting
3) Flows and Life-Cycle
4) LCA: Focus on phases
5) LCA: Systems and processes
6) Operational details and examples
The second part of the course is devoted to the use of common software for LCA. with different case studies of increasing complexity
Available for CircleU students: Yes

Introduction to Network Science

Institution: Scuola IMT Lucca
Location: IMT School for Advanced Studies Lucca, p.zza San Francesco 19, 55100 Lucca (Italy)
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: Yes
Lecturers: Tiziano Squartini
Email: tiziano.squartini@imtlucca.it
Academic Year: 2024/2025
Semester: 1
Hours: 20
Timetable: The timetable may be subject to changes: please write to phd@imtlucca.it and ask to have the calendar shared.
Abstract: The course offers a panoramic view of network science. Following its historical development, we will review the main concepts and methods of this discipline. Moving from the basic, stylized facts characterizing real-world networks, we will describe the most popular techniques to extract information from them.
Syllabus: Introduction to graph theory. Empirical properties of complex networks (scale invariance of the degree, small-world phenomenon, modularity). Network representations (monopartite, bipartite and multilayer; binary and weighted; undirected and directed networks; unsigned and signed networks; hypergraphs; simplicial complexes). Centrality. Ranking and reputation algorithms. Mesoscale structures (communities, core-periphery and bow-tie structures). A primer on dynamical models: Watts-Strogatz and Barabasi-Albert models. A primer on static models: Erdos-Renyi, Chung-Lu and fitness models.
Available for CircleU students: Yes

Introduction to sustainability and ecological economics

Institution: Scuola IMT Lucca
Location: IMT Lucca. Piazza S. Francesco 19, 55100 Lucca
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: No
Lecturers: Angelo Facchini
Email: angelo.facchini@imtlucca.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: 9-06-2025 to 4-07-2025
Abstract: What is sustainability? Which is the link between the economy and the Environment? Which are the main challenges and the main research topics? Which are the main factors that influence a transition to sustainability?
Providing the first insights to answer the above questions is the aim of this course. Lectures are devoted to the fundamental topics in the field of sustainability science and environmental economics. This last is used as a ground to explain the main differences and similarities between ecological and environmental economics, that will be highlighted and discussed with practical examples.
The course is divided into the following modules:
1. Introduction to sustainability science (lectures 1-2)
2. Basic principles of environmental and resource economics (lectures 3-7)
3. Methods and applications (lectures 8-9)
4. Advanced and research topics (lecture 10)
Syllabus: Learning Outcomes:
This course aims to provide students with fundamental concepts of sustainability science and the economics view of the environment.
Upon completion, participants will have the knowledge and skills to:
1. Have a basic understanding of the principles of environmental and ecological economics, with a clear overview on the fundamental principles for the understanding of human-economy- environment interaction
2. Have a basic understanding of environmental problems and environmental policies.
3. Have a first knowledge of the current research topics, directions, and funding opportunities.
Participants will also rely on the main topics regarding the European Green Deal and the Ecological transition.
Available for CircleU students: Yes

Legal issues on AI-Applications for vulnerable groups.

Institution: Scuola Superiore Sant’Anna
Location: Scuola Sant’Anna – Pisa Aula 5 – Sede Centrale 9-13; 14-17 & 10.1.2025 Scuola Sant’Anna Pisa Aula 5 – Sede Centrale 9-14.
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: Yes
Lecturers: Denise Amram
Email: denise.amram@santannapisa.it
Academic Year: 2024/2025
Semester: 1
Hours: 12
Timetable: The course starts on 9.1.2025
Abstract: The Course focuses on the general legal framework and tailored safeguards applicable to data analysis related to vulnerable individuals/groups and their impact on policy and law-making.
Case studies will be presented in particular on children, patients, workers, consumers.
Syllabus: 1. Overview on the regulatory framework (EU strategy on data, GDPR, AI-Act) impacting on data-driven and ai-based research life-cycles.
2. Protocols for developers, deployers, and providers of AI-based systems to process general and sensitive data.
3. Case-studies on vulnerable users: consumers, patients, children, workers.
Available for CircleU students: Yes

Machine Learning

Institution: Università di Pisa
Location: Università di Pisa – Polo Fibonacci – Largo Bruno Pontecorvo 3, 56127 Pisa, ITALY
Level: Master level
Type: Introductory course (no or few prerequisites)
Attendance Mode: In person
Exam: Yes
Lecturers: Alessio Micheli
Email: alessio.micheli@unipi.it
Academic Year: 2024/2025
Semester: 1
Hours: 72
Timetable: https://didattica.di.unipi.it/laurea-magistrale-in-informatica/orario-magistrale-informatica/
Abstract: The course introduces the machine learning principles and models, including basic theory of learning. The course provides the Machine Learning basis for both the aims of building new adaptive Intelligent Systems and powerful predictive models for Intelligent Data Analysis.
The focus is on the critical analysis of the characteristics for the design and use of the algorithms for learning functions from examples and for the rigorous experimental evaluation.
The student who successfully completes the course will be able to demonstrate a solid knowledge of the main models and algorithms for learning functions from data, with a focus on Neural Networks and related methods. The student will be aware of the general conceptual framework of modern machine learning; of the basic principles of computational learning processes; of rigorous validation techniques; of the critical characteristics for the use of the learning models to design intelligent/adaptive systems and predictive models for data analysis.

Syllabus: Computational learning tasks for predictions, learning as function approximation, generalization concept.

Basic concepts and models: Continuos and discrete hypothesis space, inductive bias, linear and nearest neighbor models (learning algorithms and properties), regularization.

Neural Networks (NN) architectures and learning algorithms: Perceptron. Multi-layers feedforward models. Deep models. Randomized NN. Recurrent NN. Regularization.

Validation: model selection and model assessment.

Principles of learning processes: Elements of Statistical Learning Theory. Bias/variance analysis.

Support Vector Machines and Kernels-based models.

Unsupervised learning: vector quantization, self-organizing map (SOM).

Introduction to benchmarks and applications.

Introduction to advanced approaches (structured domains, learning on graphs).

Available for CircleU students:

Machine Learning and Omics in Epidemiology

Institution: Università di Firenze
Location: Aule del Dipartimento di Statistica, Informatica, Applicazioni “Giuseppe Parenti”, viale Morgagni 59, 50134, Firenze
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: Yes
Lecturers: Dr. Chiara Marzi and Prof. Gianluca Severi
Email: chiara.marzi@unifi.it
Academic Year: 2024/2025
Semester: 2
Hours: 24
Timetable: May – July 2024
Abstract: This course aims at introducing Ph.D. students to statistical and machine learning methods for the analysis of high-dimensional data in epidemiology – the so-called “omics”. Particular emphasis will be placed on the different types of omics data (e.g., molecular data, metabolomics, genomics, proteomics, radiomics, etc.), as well as on the fundamental steps performed within a Machine Learning analysis to extract useful insights from these data (e.g., data harmonisation, features selection, validation scheme, etc.).
Syllabus: This course aims at introducing Ph.D. students to statistical and machine learning methods for the analysis of high-dimensional data in epidemiology – the so-called “omics”. Particular emphasis will be placed on the different types of omics data (e.g., molecular data, metabolomics, genomics, proteomics, radiomics, etc.), as well as on the fundamental steps performed within a Machine Learning analysis to extract useful insights from these data (e.g., data harmonisation, features selection, validation scheme, etc.). Material will be provided by the teachers and the exam will be a presentation of a paper – interesting from the student’s point of view – including the elements learned during the course.
Available for CircleU students: Yes

Machine Learning Methods for Physics

Institution: Università degli Studi di Genova
Location: Dipartimento di Fisica – Università di Genova
Level: Post graduate Master level
Type: Introductory course (no or few prerequisites)
Attendance Mode: In person
Exam: Yes
Lecturers: Dr. Riccardo Torre, Dr. Andrea Coccaro, Dr. Francesco Di Bello
Email: riccardo.torre@ge.infn.it
Academic Year: 2024/2025
Semester: 2
Hours: 48
Timetable: TBA, see the link https://corsi.unige.it/en/off.f/2024/ins/77984?codcla=9012

Abstract: What is a machine learning algorithm? Why is machine learning playing a primary role in physics? Which problems can be optimized using it? What is the most suitable algorithm to solve my physics problem?

These are some of the questions that this course aims to answer, providing students with the state-of-the-art knowledge regarding the usage and understanding of artificial intelligence algorithms applied to physics. The course also focuses on developing a critical comprehension of results, exploring the development of future algorithms, and the most promising technologies.

Syllabus: The course aims to:

– Introduce the concepts of minimization algorithms for a scalar functional (the loss function).
– Provide the necessary tools for practical course execution, such as Python, Tensorflow, and Pytorch.
– Cover dense neural networks and examples of their applications in physics.
– Explore convolutional neural networks and examples of their applications in physics.
– Discuss recurrent neural networks and examples of their applications in physics.
– Investigate graph neural networks: inductive bias and examples of their applications in physics.
– Examine attention mechanisms: transformers and examples of their applications in physics.
– Study generative neural networks and examples of their applications in physics.
– Provide an overview of differentiable programming.

The course encompasses these topics to provide students with a comprehensive understanding of machine learning algorithms in the context of physics applications.

Available for CircleU students: No

Markov processes

Institution: Scuola IMT Lucca
Location: Lucca, Piazza San Francesco
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: No
Lecturers: Irene Crimaldi
Email: phd@imtlucca.it
Academic Year: 2024/2025
Semester: 2
Hours: 14
Timetable: February 7 – 28, 2025
Abstract: This course covers the fundamental results regarding Markov processes with discrete state
space and discrete or continuous time. Some proofs are sketched or omitted in order to have
more time for examples, applications and exercises.
Syllabus: This course deals with the following topics:
– Markov chains (definitions and basic properties, classification of the states, invariant
measure, stationary distribution, strong law of large numbers, introduction to Markov chain
Monte Carlo method, ergodic limit theorem, cyclic classes, passage problems);
– Markov processes with discrete state space and continuous time (definition, transition
probabilities, Markov’s property, transition intensities, generator, forward Kolmogorov
equations, stationary probability distribution);
– Birth-Death processes and queues.
Available for CircleU students: Yes

MATLAB for Data Science

Institution: Scuola IMT Lucca
Location: Lucca, Piazza S. Francesco 19, IMT Lucca, Classroom to be chosen
Level: Ph.D. level
Type: Intermediate course
Attendance Mode: Blended
Exam: No
Lecturers: Giorgio Stefano Gnecco
Email: giorgio.gnecco@imtlucca.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: April 2025-May 2025
Abstract: The course provides MATLAB implementations of several machine learning techniques.
Syllabus: Presentation of MATLAB code for:
– principal component analysis;
– spectral clustering;
– linear and polynomial regression;
– bias/variance trade-off;
– resampling methods;
– bounding box identification via the quasi-Monte Carlo method;
– logistic regression;
– batch gradient descent and stochastic gradient descent for training perceptrons/multilayer neural networks;
– perceptrons/multilayer neural networks applied to the XOR problem;
– digit recognition via neural networks;
– backpropagation with momentum;
– backpropagation applied to the minimization of the cross-entropy function;
– comparison of backpropagation applied to the minimization of the cross-entropy function and of the sum of squares error function;
– spam recognition via support vector machines;
– symmetry and antisymmetry in support vector machine training problems;
– trade-off between number of examples and precision of supervision in ordinary least squares, weight least squares, and fixed effects panel data models;
– learning with boundary conditions;
– learning with mixed hard/soft constraints;
– LQG online learning;
– RBF interpolation;
– surrogate optimization for optimal material design;
– curve identification in the presence of curve intersections;
– matrix completion.
Depending on the students’ background, additional slides will be presented/provided to them, illustrating a summary of the theory behind some of the techniques considered in the course.
Available for CircleU students: Yes

Maximum-Entropy Models of Complex Systems II

Institution: Scuola IMT Lucca
Location: IMT School for Advanced Studies Lucca, p.zza San Francesco 19, 55100 Lucca (Italy)
Level: Ph.D. level
Type: Advanced course
Attendance Mode: Blended
Exam: Yes
Lecturers: Tiziano Squartini
Email: tiziano.squartini@imtlucca.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: The timetable may be subject to changes: please write to phd@imtlucca.it and ask to have the calendar shared.
Abstract: The course heavily focuses on deeper theoretical aspects of maximum-entropy models and their consequences. Particular emphasis will be put on maximum-entropy models to study weighted complex networks.
Syllabus: How to build statistical models in a principled way: a review of maximum-entropy models. From null models to true models: weighted reciprocal configuration models and block-structured models. Bipartite formalism for Exponential Random Graph models. Continuous formalism for Exponential Random Graph models. Conditional framework for discrete and continuous Exponential Random Graph models. Information criteria for model selection (Likelihood Ratio Test, Akaike Information Criterion, Bayesian Information Criterion, Minimum Description Length). Applications to economic and financial systems. The course will include an overview of ongoing research carried out by Networks@IMT, thereby offering directions for possible PhD projects in this area.
Available for CircleU students: Yes

Microeconometrics

Institution: Scuola Superiore Sant’Anna
Location: Piazza Martiri della Libertà 33, Pisa
Level: Ph.D. level
Type: Advanced course
Attendance Mode: In person
Exam: Yes
Lecturers: Laura Magazzini
Email: laura.magazzini@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 21
Timetable: To be decided. It will be held in the period February-March. Contact the lecturer for further details and updates.
Abstract: The course aims at providing students the tools for dealing with microeconomic analysis of the behavior of individuals or firms. Regression methods for the study of static and dynamic panel data models and estimation of limited dependent variable models will be considered, including discrete choice models, count data models, censored and truncated data. Besides the theoretical background, students will be exposed to the discussion and the analysis of empirical applications. (the course requires basic knowledge of OLS and IV regression methods and maximum likelihood estimation).
Syllabus: Linear panel data models: static and dynamic framework; Non linear regression models (binary choice, count data, truncation and censoring).
Available for CircleU students:

Network Neuroscience and MEdicine

Institution: Scuola IMT Lucca
Location: Lucca, IMT, Piazza San Francesco 19
Level: Ph.D. level
Type: Advanced course
Attendance Mode: Blended
Exam: Yes
Lecturers: Tommaso Gili
Email: tommaso.gili@imtlucca.it
Academic Year: 2024/2025
Semester: 1
Hours: 20
Timetable: From 12/02/2025 to 27/02/2025
Abstract: We will discuss modelling brain function and structure using complex networks. It will be shown how passing from neurovascular and electrophysiological measurements to graphs is possible and how a connectome can be obtained. We will present mesoscopic models of communication in the brain and the role of synchronisation. The tools used to study the brain will also be shown to be useful in medicine by discussing the interactome, the diseasome and the foodome.
Syllabus: What is a complex system, and why can the brain be considered complex?
Neurovascular coupling.
The BOLD signal.
From BOLD time-series to a graph.
Molecular diffusion of water in the brain and fiber-tracking,
The structural architecture of the brain.
Electrophysiological signals.
Origin of EEG signal.
Origin of MEG signal.
Definition of functional networks from M/EEG time series.
Topological measures used in neuroscience and their application.
Higher-order interactions in the brain.
Models of communication in the brain.
Communication through synchronisation.
Synchronisation and symmetry.
Coarse-graining network neuroscience.
Higher-order interactions.
Null-models for Network Neuroscience.
Protein-protein interaction networks (interactome).
Human disease networks (diseasome).
Networks in systems pharmacology.
Boolean networks for system biology.
Food-health interaction (foodome).
Available for CircleU students: Yes

Network Reconstruction

Institution: Scuola IMT Lucca
Location: IMT School for Advanced Studies Lucca, p.zza San Francesco 19, 55100 Lucca (Italy)
Level: Ph.D. level
Type: Intermediate course
Attendance Mode: Blended
Exam: Yes
Lecturers: Tiziano Squartini
Email: tiziano.squartini@imtlucca.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: The timetable may be subject to changes: please write to phd@imtlucca.it and ask to have the calendar shared.
Abstract: The course focuses on the topic of network reconstruction. Early attempts to infer missing information about networks will be reviewed, putting particular emphasis on the use of such techniques to reconstruct financial networks.
Syllabus: Literature review about network reconstruction. Early attempts to infer a network structure from partial information (MaxEnt approach; the copula approach; MECAPM; Iterative Proportional Fitting algorithm; Minimum Density algorithm). Monopartite and bipartite financial networks reconstruction via the fitness model. Systemic risk estimation. How to build statistical models in a principled way: maximum-entropy models. Econometric VS maximum-entropy models: a comparison.
Available for CircleU students: Yes

Neural Networks and Deep Learning: Advanced Topics

Institution: Scuola Superiore Sant’Anna
Location: See link at: https://retis.santannapisa.it/~giorgio/courses/neural/nn.html
Level: Ph.D. level
Type: Advanced course
Attendance Mode: Online
Exam: Yes
Lecturers: Giorgio Buttazzo
Email: giorgio.buttazzo@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: See link at: https://retis.santannapisa.it/~giorgio/courses/neural/nn.html
Abstract: This caurse presents recent techniques proposed to improve classical neural netowork models and overcome their limitations. Topics include model compression, semi-supervised learning, contrastive learning, neural networks for object tracking, adversarial attacks and defense methods.
Syllabus: 1. Model compression. Weight quantization. Model pruning. Model distillation.
2. Semi-supervised learning. K-nearest neighbors. Self-training algorithms.
3. Contrastive learning and Supervised Contrastive Learning.
4. Neural networks for object tracking.
5. Trustworthy AI. Safety, security, and predictability issues in deep neural networks.
6. Adversarial attacks and defenses.
7. Explainable AI.
8. Anomaly detection and domain generalization.
9. Attention mechanisms in computer vision and visual transformers.
Available for CircleU students: Yes

Neural Networks and Deep Learning: Deep Networks

Institution: Scuola Superiore Sant’Anna
Location: See link at: https://retis.santannapisa.it/~giorgio/courses/neural/nn.html
Level: Ph.D. level
Type: Intermediate course
Attendance Mode: Online
Exam: Yes
Lecturers: Giorgio Buttazzo
Email: giorgio.buttazzo@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: https://retis.santannapisa.it/~giorgio/courses/neural/nn.html
Abstract: This module presents the foundations for understanding deep neural networks and deep learning algorithms. Topics include convolutional networks for classification, detection and segmentation, deep reinforcement learning, generative adversarial networks and transformers.
Syllabus: 1. Problems and solutions to extend small networks to deep networks.
2. Convolutional networks.
3. Networks for object classification.
4. Networks for object detection.
5. Networks for image segmentation.
6. Deep Reinforcement Learning.
7. Generative adversarial networks.
8. Recurrent neural networks.
9. Attention mechanism.
10. Transformers
Available for CircleU students: Yes

Neural Networks and Deep Learning: Implementation Issues

Institution: Scuola Superiore Sant’Anna
Location: See link at: https://retis.santannapisa.it/~giorgio/courses/neural/nn.html
Level: Ph.D. level
Type: Advanced course
Attendance Mode: Online
Exam: Yes
Lecturers: Giorgio Buttazzo
Email: giorgio.buttazzo@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 30
Timetable: See link at: https://retis.santannapisa.it/~giorgio/courses/neural/nn.html
Abstract: The aim of this course is to discuss practical and implementation issues useful to
deploy neural networks on a variety of embedded platforms using different languages and
development environments.
Syllabus: 1. Implementing Neural Networks from scratch in C.
2. Development frameworks: Tensorflow, Keras, Caffe, and Pytorch.
3. Functional components in autonomous driving.
4. The Apollo framework for autonomous driving.
5. Simulators for autonomous driving: the CARLA simulator.
6. DNN optimization for embedded platforms.
7. Accelerating deep networks on GPGPUs.
8. Overview of the Nvidia TensorRT framework.
9. Accelerating deep networks on FPGA using Xilinx Deep Processing Unit.
Available for CircleU students: Yes

Neural Networks and Deep Learning: Theoretical Foundations

Institution: Scuola Superiore Sant’Anna
Location: See channel at: https://retis.santannapisa.it/~giorgio/courses/neural/nn.html
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Online
Exam: Yes
Lecturers: Giorgio Buttazzo
Email: giorgio.buttazzo@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: https://retis.santannapisa.it/~giorgio/courses/neural/nn.html
Abstract: The aim of the course is to provide key concepts and methodologies to understand
neural networks, explaining how to use them for pattern recognition, image classification, signal prediction, system identification, and adaptive control.
Syllabus: 1. Introduction to neural computing.
2. Fully connected networks.
3. Unsupervised learning.
4. Clustering algorithms.
5. Autoencoders.
6. Reinforcement Learning.
7. Supervised learning
8. The Backpropagation algorithm.
9. Applications of neural networks to classification, signal prediction, and control.
10. Radial basis functions networks.
Available for CircleU students: Yes

Numerical Linear Algebra in Python

Institution: Scuola Superiore Sant’Anna
Location: Scuola Superiore Sant’Anna
Level: Master level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: Yes
Lecturers: Giovanni Stabile
Email: giovanni.stabile@santannapisa.it
Academic Year: 2024/2025
Semester: 1
Hours: 20
Timetable: Started last week of october, all the classes are recorded
Abstract: The course deals with the theory and practical implementation of numerical methods for linear algebra problems. Specific topics include the solution of linear systems of equations using both direct and iterative methods, numerical methods for the approximation of eigenvalues and eigenvectors, numerical solution of nonlinear equations and systems of nonlinear equations. Particular emphasis is devoted to the implementation aspects using the python programming language.
Syllabus: no syllabus
Available for CircleU students: Yes

OpenFOAM laboratory

Institution: Scuola Superiore Sant’Anna
Location: Scuola Superiore Sant’Anna Pisa
Level: Master level
Type: Intermediate course
Attendance Mode: Blended
Exam: Yes
Lecturers: Giovanni Stabile
Email: giovanni.stabile@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 10
Timetable: March – May
Abstract: This course introduces the open source toolbox, OpenFOAM a widely used library for computational fluid dynamics. It provides a foundation for all aspects of OpenFOAM, from running cases to programming, so is useful to both new users and existing users wishing to broaden their basic knowledge of OpenFOAM.
Syllabus: no syllabus
Available for CircleU students: Yes

Optimal Control and Differential Games

Institution: Scuola IMT Lucca
Location: Lucca, Piazza S. Francesco 19, IMT Lucca, Classroom to be chosen
Level: Ph.D. level
Type: Intermediate course
Attendance Mode: Blended
Exam: Yes
Lecturers: Giorgio Stefano Gnecco
Email: giorgio.gnecco@imtlucca.it
Academic Year: 2024/2025
Semester: 1
Hours: 20
Timetable: December 2024-January 2025
Abstract: The course provides an overview of optimal control theory for the deterministic and stochastic cases. Both discrete-time and continuous-time problems are considered, together with some applications to economics.
Syllabus: – An overview of optimal control problems.
– An economic example of an optimal control problem: the cake-eating problem.
– Dynamic programming and Bellman’s equations for the deterministic discrete-time case.
– Reachability/controllability and observability/reconstructability for time-invariant linear dynamical systems.
– The Hamilton-Jacobi-Bellman equation for continuous-time deterministic optimal control problems.
– Pontryagin’s principle for continuous-time deterministic optimal control problems.
– LQ optimal control in discrete time for deterministic problems.
– Application of dynamic programming to stochastic and infinite-horizon optimal control problems in discrete time.
– LQ optimal control in discrete time for stochastic problems and Kalman filter.
– Introduction to approximate dynamic programming and reinforcement learning.
– An economic application of optimal control: a dynamic limit pricing model of the firm.
– An introduction to differential games: an application to transboundary pollution.
Available for CircleU students: Yes

Predictive Models for Time Series Analysis

Institution: Università di Pisa
Location: Pisa, Largo B. Pontecorvo, Building C, Room Seminari Est, Dept. C.S.
Level: Post graduate Master level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: Yes
Lecturers: Riccardo Guidotti
Email: riccardo.guidotti@unipi.it
Academic Year: 2024/2025
Semester: 2
Hours: 24
Timetable: First three weeks of April
Abstract: This course on Time Series Analytics is designed to equip students with comprehensive knowledge and skills to analyze, interpret, and build predictive models for time series data. The course covers fundamental concepts, including time series components, normalizations, stationarity, autocorrelation, approximation and various forms of time series transformations, while delving into predictive models passing from DTW based kNN to state-of-the-art kernel-based and dictionary-based approaches. Emphasis is placed on both the theoretical underpinnings and practical applications of these techniques in general-purpose domains. By the end of the course, participants will have developed the analytical acumen and technical expertise necessary to conduct independent research and contribute novel insights to the field of time series analysis. This course is essential for aspiring data scientists, quantitative analysts, and researchers seeking to deepen their understanding and application of time series methods.
Syllabus: 1. Introduction & Preprocessing (4 hours)
2. Distances, Approximation & Global Features (4 hours)
3. Classification & Regression Part 1 (4 hours)
4. Classification & Regression Part 2 (4 hours)
5. Forecasting (4 hours)
6. In-class Project
Available for CircleU students: Yes

Programming & Data Analytics & Process-oriented Data Science for non-computer scientists (PDAI1 & PDAI2-PM)

Institution: Scuola Superiore Sant’Anna
Location: Piazza Martiri della Liberta’ 33, Pisa
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: Yes
Lecturers: Andrea Vandin, Daniele Giachini
Email: andrea.vandin@santannapisa.it
Academic Year: 2024/2025
Semester: 1, 2
Hours: 40
Timetable: https://github.com/EMbeDS-education/ComputingDataAnalysisModeling20242025/wiki/General-Calendar

Abstract: This course is structured in three modules of 20-hours each (PDAI1, PDAI2-ML, PDAI2-PM) that students can attend in different years. PDAI1 is offered each year, while the other two alternate. PDAI1 is preparatory to the other two, which can be taken independently of each other. In this A.Y., PDAI1 and PDAI2-PM will be offered.

The course provides a well-structured introduction to the fundamentals of (object-oriented) programming (PDAI1), data processing and artificial intelligence (PDAI2-ML), and process-oriented data science (process mining, PDAI2-PM). The course will focus on how to create good quality software (PDAI1), on how to carry out good quality data analysis and artificial intelligence projects (PDAI2-ML), and on research-oriented aspects related to process-oriented data science, in particular on process mining, where the aim is to analyse and optimise the data-generating process (PDAI2-PM). The student who has achieved the course objectives will gain an understanding of the problems and tasks related to structured programming, data analysis and machine learning in order to be able to make informed decisions. The student will be able to write Python programmes of various kinds, with a focus on complex data analysis and AI tasks, and process mining.

Syllabus: • PDAI 1 introduces students to the fundamental principles of structured programming, with basic applications to data processing. It starts from basic notions of programming (variables, data types, collections, control & repetition structures, functions & modules), and progresses to basic data processing functionalities (loading, manipulation, and visualization of CSV data).
• PDAI 2-ML introduces students to the components of typical data analysis processes and machine learning pipelines. It first builds the necessary toolset by introducing popular Python libraries for data manipulation/visualization (NumPy, Pandas, Seaborn, scikit-learn) with simple applications. The toolset is then applied to a more complex case study on the classification of benign and malignant breast cancer, including aspects of data preprocessing, dimensionality reduction, clustering, and classification. The course will conclude with one research-driven topics like process-oriented data science (Process Mining).
• PDAI 2-PM introduces students to recent data-driven techniques where the main component is the process that generated the data (the data generating process). This is a particularly hot topic, with many companies and researchers involved (see, e.g., the list of industrial that sponsored the reference conference in 2023 https://icpmconference.org/2023/sponsor-and-exhibition/). We will consider techniques known as Process Mining, in which logs generated during the execution of a process (e.g., an industrial production process, business processes, social system ‘processes’) are used to infer the structure of the process. Questions of interest are, e.g.: What is the actual process being executed? Are there possibilities for improvement? Does the actual process conform to the intended reference process?
Available for CircleU students: Yes

Random effects models for multilevel and longitudinal data

Institution: Università di Firenze
Location: Dept. of Statistics, Computer Science, Applications, University of Florence, viale Morgagni 59, 50134 Firenze.
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: In person
Exam: Yes
Lecturers: Leonardo Grilli, Carla Rampichini
Email: leonardo.grilli@unifi.it
Academic Year: 2024/2025
Semester: 1
Hours: 12
Timetable: 27 to 30 January 2025, 10:00-13:00
Abstract: The course introduces the theory and practice of random effects (mixed effects) models for the analysis of multilevel data in both cross-sectional and longitudinal settings. Emphasis is placed on model specification and interpretation. The course covers random effects models for continuous responses and for categorical responses.
Syllabus: Part A: continuous responses
Introduction
Basics of the two-level linear model: no covariates (random effects ANOVA); covariates at level 1; covariates at level 2
Inference
Between, within and contextual effects
Fixed effects versus random effects
Model specification and ESS example
Sample size requirements
Complex sampling designs
Multiple levels of nesting
Non-hierarchical structures
Software & Books
Part B: binary responses
Review of the standard logit model for binary responses
The random effects logit models for binary responses
Predicted probabilities
The latent response specification: measurement scale and estimable parameters
Maximum likelihood via Gaussian quadrature
Available for CircleU students:

Responsible Artificial Intelligence

Institution: Università di Pisa
Location: Dipartimento di Informatica, Università di Pisa, Largo B. Pontecorvo 3, 56125 Pisa, Italy
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: Yes
Lecturers: Anna Monreale, Francesca Naretto, Salvatore Ruggieri
Email: anna.monreale@unipi.it
Academic Year: 2024/2025
Semester: 2
Hours: 24
Timetable: The course will be offered in one week to be fixed during the second semester.
Abstract: This course presents technologies enabling the design and development of Responbile Artificial Intelligent (AI) systems. In particular, it first introduces notions of privacy, anonymity, transparency, fairness, and uncertainty in AI considering the Euroepan legal framework and how they can be modelled for enabling the developement of methods for quantitatively assessing the AI system vulnerabilities and trustworthiness and for mitigating the identified risks and unethical behaviour.
The course then presents technologies for implementing the privacy-by-design principle, for auditing AI-based predictive models, and for the protection of users rights with the goal of enabling explanable, pribacy-aware, fairness-aware and self-assessed uncertainty AI models.
Syllabus: The course will cover the following topics: privacy in big data and AI, bias and fairness in AI, self-assessed uncertainty AI models, explainable AI, self-assessed uncertainty AI models.
Available for CircleU students: Yes

Responsible Generative AI

Institution: Scuola Normale Superiore
Location: Scuola Normale Superiore, Palazzo della Carovana
Level: Ph.D. level
Type: Advanced course
Attendance Mode: Blended
Exam: Yes
Lecturers: Prof. Fosca Giannotti, Dr. Gizem Gezici
Email: gizem.gezici@sns.it, fosca.giannotti@sns.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: https://docs.google.com/document/d/1XURfLr725RcIXdoBHiaLdrwmPI-Awy3N/edit
Abstract: The rapid development and deployment of generative AI models and applications has the potential to revolutionise various domains which brings about the urgency to use these models in a responsible manner. Generative AI refers to creating new content in different modalities of digital text, images, audio, code and other artefacts based on already existing content. Text generator models such as GPT-4, and its chat version, ChatGPT as well as text to image models such as DALL-E 3 and Stable Diffusion are popular generative AI models. Although these models have significant implications for a wide spectrum of domains, there are several ethical and social considerations associated with generative AI models and applications. These concerns include the existence of bias, lack of interpretability, privacy, fake and misleading content such as hallucinations. Thus, it is very crucial to discuss these risks with their corresponding potential safeguards (if any) in addition to the technical details of these powerful models.
The course is organized as follows in three modules: i) an introductory one presenting main motivations as well as main concepts in NLP and further generative AI; ii) an advanced module providing technical details about the building blocks of foundation models with the main focus on the text generation models which also includes an hands-on session on LLMs; iii) an advanced module providing the main risks of generative AI with the corresponding technical considerations and challenges to establish responsible generative AI models in practice which includes a hands-on session as well.
Syllabus: https://docs.google.com/document/d/1XURfLr725RcIXdoBHiaLdrwmPI-Awy3N/edit
Available for CircleU students: No

Seminari multidisciplinari (in inglese, formula ibrida): “AI and diversity”

Institution: Università degli Studi di Napoli L’Orientale
Location: University of Naples L’Orientale
Level: Ph.D. level
Type: Cycle of seminars
Attendance Mode: Blended
Exam: No
Lecturers: Moretti/Pezzella, ART-ER; Cicatiello/Gaeta, UniOr; Vanmassenhowe, University of Tilburg; Monti/Di Buono, UniOr; Ruotolo, UniFG; Cataldi/Pace, UniOr; Numerico, UniRoma3; Terranova/Portanova, UniOr
Email: jmonti@unior.it
Academic Year: 2024/2025
Semester: 2
Hours: 9
Timetable: 12 marzo, 15:00/17:30, Giorgio Moretti e Dario Pezzella, Area Programmazione Strategica e Studi di ART-ER S. cons. p. a., Artificial intelligence, data and policies for research and innovation. The case of Emilia-Romagna, discussants Lorenzo Cicatiello/Lucio Gaeta (Università di Napoli L’Orientale); 27 marzo, 10:30/12:30, Eva Vanmassenhowe, University of Tilburg, “We can fix that”: A Decade of Gender Bias in MT, discussants Johanna Monti/M. Pia Di Buono (Università di Napoli L’Orientale); 14 aprile, 10:30/12:30, Giampaolo Ruotolo, Università di Foggia, Artificial Intelligence and international law against discrimination: some trends in light of latest practice, discussants Giuseppe Cataldi, Marianna Pace (Università di Napoli L’Orientale); (data da stabilire), Teresa Numerico, Università Roma Tre, AI and the Quest for Universality: Is Decolonizing AI Possible?, discussants Tiziana Terranova/Stamatia Portanova (Università di Napoli L’Orientale);
Abstract: Series of seminars (in English and hybrid mode) , in collaboration with the Jean Monnet Center of Excellence Artificial Intelligence and Communication in a Digitalised European Democracy (AICoDED) of the University of Naples L’Orientale.
The workshop explores the topics of artificial intelligence and communication from an interdisciplinary perspective.
Syllabus: 12 marzo, 15:00/17:30, Giorgio Moretti e Dario Pezzella, Area Programmazione Strategica e Studi di ART-ER S. cons. p. a., Artificial intelligence, data and policies for research and innovation. The case of Emilia-Romagna, discussants Lorenzo Cicatiello/Lucio Gaeta (Università di Napoli L’Orientale); 27 marzo, 10:30/12:30, Eva Vanmassenhowe, University of Tilburg, “We can fix that”: A Decade of Gender Bias in MT, discussants Johanna Monti/M. Pia Di Buono (Università di Napoli L’Orientale); 14 aprile, 10:30/12:30, Giampaolo Ruotolo, Università di Foggia, Artificial Intelligence and international law against discrimination: some trends in light of latest practice, discussants Giuseppe Cataldi, Marianna Pace (Università di Napoli L’Orientale); (data da stabilire), Teresa Numerico, Università Roma Tre, AI and the Quest for Universality: Is Decolonizing AI Possible?, discussants Tiziana Terranova/Stamatia Portanova (Università di Napoli L’Orientale);
Available for CircleU students: Yes

Social network analysis

Institution: Università di Pisa, Consiglio Nazionale delle Ricerche
Location: University of Pisa, Largo Bruno Pontecorvo
Level: Master level
Type: Introductory course (no or few prerequisites)
Attendance Mode: In person
Exam: Yes
Lecturers: Dino Pedreschi, Giulio Rossetti
Email: giulio.rossetti@isti.cnr.it, dino.pedreschi@unipi.it
Academic Year: 2024/2025
Semester: 2
Hours: 48
Timetable: https://didattica.di.unipi.it/en/master-programme-in-data-science-and-business-informatics/academic-calendar-2024-2025/
Abstract: Over the past decade there has been a growing public fascination with the complex “connectedness” of modern society. This connectedness is found in many contexts: in the rapid growth of the Internet and the Web, in the ease with which global communication now takes place, and in the ability of news and information as well as epidemics and financial crises to spread around the world with surprising speed and intensity. These are phenomena that involve networks and the aggregate behavior of groups of people; they are based on the links that connect us and the ways in which each of our decisions can have subtle consequences for the outcomes of everyone else. This course is an introduction to the analysis of complex networks, with a special focus on social networks and the Web – their structure and function, and how it can be exploited to search for information. Drawing on ideas from computing and information science, applied mathematics, economics and sociology, the course describes the emerging field of study that is growing at the interface of all these areas, addressing fundamental questions about how the social, economic, and technological worlds are connected. Data-driven analysis of complex networks using a variety of models and software tools.
Syllabus: Real-world network characterization:
Big graph data and social, information, biological and technological networks
The architecture of complexity and how real networks differ from random networks: node degree and long tails, social distance and small worlds, clustering, and triadic closure.
Comparing real networks and random graphs. The main models of network science: small world and preferential attachment.
Assortativity and homophilic behaviors.
Strong and weak ties, community structure, and long-range bridges.
Network beyond pairwise interactions: high-order network modeling.
Applications:
Robustness of networks to failures and attacks.
Dynamic Network modeling.
Dynamic Community Discovery.
Link Prediction
Cascades and spreading.
Network models for opinion dynamics and epidemics.
Available for CircleU students: No

Statistical Learning and Large Data (SLLD)

Institution: Scuola Superiore Sant’Anna
Location: Piazza Martiri della Libertà, 33 56127 Pisa (Italia)
Level: Post graduate Master level
Type: Intermediate course
Attendance Mode: Blended
Exam: Yes
Lecturers: Francesca Chiaromonte
Email: francesca.chiaromonte@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 40
Timetable: https://github.com/EMbeDS-education/ComputingDataAnalysisModeling20242025/wiki/General-Calendar
Abstract: This course will introduce the students to various topics in contemporary Statistical Learning and to methods used to analyze the large, complex datasets that are increasingly common in many scientific fields. The content will be organized in two Modules that the students can attend in different years. Compared to traditional courses, the focus will be on analyzing actual datasets of interest to the students through group projects and Practicum sessions associated to each lecture.
Syllabus: Module 1
– Unsupervised classification; Clustering methods
– Unsupervised dimension reduction; Principal Components Analysis and related techniques
– Supervised classification methods
– Non-parametric regression methods
– Resampling methods, Cross Validation, the Bootstrap and permutation-based techniques.
Prerequisites: a working knowledge of basic statistical inference (point estimation, confidence intervals, testing) and linear and generalized linear models. This may be obtained, or refreshed, through Applied Statistics.
Evaluation: Group project with final presentation and written report.
Materials: An Introduction to Statistical Learning – with Applications in R (James, Witten, Hastie, Tibshirani; Springer). Links to further material will be provided as needed.
Module 2
– Feature selection and regularization techniques for high-dimensional Linear and Generalized Linear Models
– Feature screening algorithms for ultra-high dimensional supervised problems
– Supervised dimension reduction; Sufficient Dimension Reduction and related techniques
– Subsampling/partitioning approaches for ultra-high sample sizes
– Under- and oversampling approaches for data rebalancing
Prerequisites: a working knowledge of the methods comprised in Module 1.
Evaluation: Group project with final presentation and written report.
Materials: An Introduction to Statistical Learning – with Applications in R (James, Witten, Hastie, Tibshirani; Springer). Computer Age Statistical Inference (B. Efron, T. Hastie). Links to further material will be provided as needed.
Available for CircleU students: No

Statistics for Machine Learning

Institution: Università di Pisa
Location: Dipartimento di Informatica, Università di Pisa, Largo B. Pontecorvo 3, 56125 Pisa, Italy
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: Yes
Lecturers: Salvatore Ruggieri
Email: salvatore.ruggieri@unipi.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: The course will be offered in one week to be fixed during the second semester.
Abstract: The student who completes successfully the course will have a solid knowledge on the main concepts and tools of statistical analysis, including the definition of a statistical model, the inference of its parameters with confidence intervals, the use of hypothesis testing, bayesian and causal inference, with specific applications to problems and models useful in (supervised) machine learning.
Syllabus: The program covers the basic methodologies, techniques and tools of statistical analysis. This includes basic knowledge of probability theory, random variables, convergence theorems, statistical models, estimation theory, hypothesis testing, bayesian inference, causal reasoning. Other topics covered include bootstrap, expectation-maximization, and applications to machine learning problems.
Available for CircleU students:

Stochastic processes

Institution: Scuola IMT Lucca
Location: Lucca, Piazza San Francesco
Level: Ph.D. level
Type: Advanced course
Attendance Mode: Blended
Exam: No
Lecturers: Irene Crimaldi
Email: phd@imtlucca.it
Academic Year: 2024/2025
Semester: 2
Hours: 18
Timetable: March 17 – April 11
Abstract: This course aims at introducing some important stochastic processes (please, note that the
general theory on Markov processes is excluded from this course, because there is a specific
course on it). Some proofs are sketched or omitted in order to have more time for examples,
applications and exercises.
Syllabus: This course deals with the following topics:
– Poisson process (definition, properties and applications);
– Conditional expectation (definition, properties);
– Martingales and co. (definitions and basic properties, Burkholder transform, stopping theorem
and some applications, predictable compensator and Doob decomposition, some convergence
results, game theory interpretation, variants);
– Wiener process (definition, some properties, Donsker theorem, Kolmogorov-Smirnov test);
– Introduction to stochastic processes with reinforcement (definition, applications, classical
models, recent models, ongoing research).
Available for CircleU students: Yes

The use of AI in criminal justice: theoretical, social and legal implications

Institution: Scuola Superiore Sant’Anna
Location: Piazza Martiri della Libertà, 33, Pisa
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: Yes
Lecturers: Gaetana Morgante, Gaia Fiorinelli
Email: Gaia.Fiorinelli@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 10
Timetable: To be decided. Contact the lecturers for further information
Abstract: The course focuses on the use of artificial intelligence (AI) in criminal justice, covering all phases from policing to risk assessment, sentencing and detention. It aims to provide students with a critical understanding of the theoretical, social and legal implications of the use of AI in these contexts, with reference to AI regulations, fundamental rights, and criminal law principles. Particular attention will be devoted to recent international, European and national frameworks and policies, such as the AI Act, the Council of Europe Framework Convention on AI, and EU/CoE recommendations and resolutions on AI in criminal justice. In addition, the course will explore how AI challenges and potentially reshapes traditional criminal law concepts related to risk assessment and responsibility. No prior knowledge of criminal law is required, as the course is intended to foster interdisciplinary dialogue among students from different academic backgrounds.
Syllabus: – The use of AI in predictive policing: applications, risks and legal safeguards.
– AI in criminal risk assessment and the evolving notions of dangerousness and recidivism.
– The use of AI in sentencing: criminal justice between fairness and bias.
– AI in prisons and probation and its impact on detainees’ fundamental rights and rehabilitation.
– The use of AI for corporate criminal compliance: opportunities and risks.
Available for CircleU students: No

Time Series Analysis

Institution: Scuola Superiore Sant’Anna
Location: Piazza Martiri della Libertà 33, Pisa
Level: Ph.D. level
Type: Advanced course
Attendance Mode: In person
Exam: Yes
Lecturers: Matteo Barigozzi
Email: laura.magazzini@santannapisa.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: 3/2/2024 ore 14-17
4/2/2024 ore 9.30-12.30
5/2/2024 ore 9.30-12.30
10/2/2024 ore 14-17
11/2/2024 ore 9.30-12.30
12/2/2024 ore 9.30-12.30
17/2/2024 ore 14-16
Abstract: The course aims to cover basic topics in time-series with focus on macroeconomic and financial applications. It will cover univariate and multivariate time serieswith a focus on linear models and their estimation. Such tools are essential for PhD students who aspire to conduct careful, state-of-the-art empirical research. In addition, the course will provide general guidance on formulating and executing (empirical) research ideas.
Syllabus: – Stationarity of univariate time series
– ARMA
– Unit roots
– Forecasting
– Non linear models for volatiltiy ARCH GARCH
– Stationarity of multivariate time series
– Wold representation
– VAR
– Unit roots and cointegration
– VECM
– Impulse response analysis
– Structural time series models
– Kalman filter
Available for CircleU students:

Towards Interpretable Neural-symbolic Artificial Intelligence

Institution: Università di Siena
Location: via Roma 56, 53100, Siena
Level: Ph.D. level
Type: Introductory course (no or few prerequisites)
Attendance Mode: Blended
Exam: Yes
Lecturers: Michelangelo Diligenti, Francesco Giannini
Email: francesco.giannini@sns.it, michelangelo.diligenti@unisi.it
Academic Year: 2024/2025
Semester: 2
Hours: 20
Timetable: The course will be held in the A.Y. 2025/26
Abstract: Artificial Intelligence (AI) has witnessed remarkable progress in recent years, particularly in the fields of deep learning and neural networks. While these advances have led to unprecedented performances in various applications, they have also raised significant ethical and security questions, which are exacerbated by the lack of interpretability of the decision mechanism of AI systems. These limitations have sprinkled the research on explainable AI (XAI), which has brought the introduction of a wide class of methodologies aiming at explaining an existing black-box model. Another relevant research direction is to explicate the formal reasoning process of a machine learning system, hence making the inference process more transparent. A possible attempt in this regard is to represent all the available knowledge about a problem as a Knowledge Graphs (KG), where the logic knowledge is represented as a graph connecting related concepts, which can be processed using neural networks, leading to a class of models known as Knowledge Graph Embeddings (KGE). More direct attempts to model human reasoning have been carried out within the areas of Statistical Relational AI (StarAI) and Neural-Symbolic (NeSy) AI, which tackle this challenge by combining symbolic reasoning with probabilistic graphical models and neural networks, respectively.
This course will cover the following topics: (i) a brief introduction to the basic notions about neural networks and symbolic reasoning, (ii) a survey on the existing categories of XAI methodologies with special attention to some popular models; (iii) a comprehensive review of the current status of the research on StarAI and NeSy, presenting state-of-the-art algorithms and models; (iv) finally, we will outline the currently open research questions and possible future directions to encourage progress and innovation towards the development of interpretable-by-design NeSy approaches.
Syllabus: Program:
• Introduction to Neural Networks and Knowledge Representation, and Reasoning
• Explainable AI principles and methodologies
• Neural-Symbolic integration: concepts, methods and implementations
• Future research directions
Available for CircleU students: Yes

Visual analytics

Institution: Università di Pisa, Consiglio Nazionale delle Ricerche
Location: University of Pisa. Location to be announced
Level: Master level
Type: Intermediate course
Attendance Mode: Blended
Exam: Yes
Lecturers: Salvatore Rinzivillo
Email: rinzivillo@isti.cnr.it
Academic Year: 2024/2025
Semester: 2
Hours: 48
Timetable: Twice a week
Abstract: The module aims at preparing students to the approprieted presentation of data and knowledge extracted from them through visualization tools and narratives that exploit multimedia.
The module first presents the basic visualization techniques for the effective presentation of information from several different sources: structured data (relational, hierarchies, trees), relational data (social networks), temporal data, spatial data and spatio-temporal data.
Syllabus: -Metaphors of information visualization.
* Hierarchical and structural
* Relational
* Temporal
* Spatial
* Temporal space
* Unstructured information (text)
– Methods and Tools.
* Overview of existing visualization environments and libraries.
– Visual Analytics Processes.
* Definition of a knowledge discovery process.
* Integrated environments for Visual Analytics.
* Exploratory visual analytics of data and models.
* Examples and case studies
Available for CircleU students: Yes