In this course, we will provide an introduction about socially aware robotics and the recent advances in deep learning with a particular coverage on its application on the most related vision tasks, e.g. face detection, facial landmark localisation and soft bio analysis. Following that, we will introduce the well-known Robotic Operating System (ROS) and learn how to deploy simple visual perception algorithms to run on general robotic platforms. The course provides the essential ingredients to enable PhD students to demonstrate AI modules on robotic platforms, such as the ARI humanoid robot who recently joined the UniTN family.

1) the European Statistical System (ESS), the Data Production Model (DPM) and the main economic aggregates to study poverty and on the surveys on households (poverty and living conditions; EUSilc survey, Household Budget Survey, Labour Force Survey).

2) the main survey designs and their estimation strategy for planned domains of study (Regions); R codes for the application of the main direct estimators of the indicators (EURAREA and SAMPLE project libraries)

At the end of the course student will be able to deal with the ESS and to criticize the statistical quality of the published indicators of poverty and living conditions (Laeken Indicators).

Module 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).

Module 2 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 module also presents KNIME, a popular python-integrated workflow-based language for data analysis.
Prerequisites: Knowledge of computer programming obtained attending Module 1.

Prerequisites: No prerequisites.
Evaluation Group project with final presentation and Jupyter notebook documentation.
Materials: Learning Python (M. Lutz). Statistics and Machine Learning in Python (E.Duchesnay, T.Löfstedt, F.Younes).

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.

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

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.

Prerequisites: a working knowledge of basic statistical inference (point estimation, confidence intervals, testing) and linear and generalized linear models. E.g., this may be obtained, or refreshed, through course Applied Statistics.

1) data collection methods

2) the use of secondary sources in data production

3) the use of R

At the end of the course student will be able to deal with traditional and modern data collection methods and will be able to present a simple policy paper using data from official surveys or other sources.