Doctoral courses

Explore the doctoral courses offered by the ELLIS Italy network, designed to train the next generation of AI researchers and practitioners.

Trustworthy artificial intelligence

University of Genoa Unit Genoa

TAI (PhD)

It has been argued that Artificial Intelligence (AI) is experiencing a fast process of commodification. This characterisation is of interest for big IT companies, but it correctly reflects the current industrialization of AI. This phenomenon means that AI systems and products are reaching the society at large and, therefore, that societal issues related to the use of AI and Machine Learning (ML) cannot be ignored any longer. Designing ML models from this human-centered perspective means incorporating human-relevant requirements such as reliability, fairness, privacy, and interpretability, but also considering broad societal issues such as ethics and legislation. These are essential aspects to foster the acceptance of ML-based technologies, as well as to be able to comply with an evolving legislation concerning the impact of digital technologies on ethically and privacy sensitive matters. *Teaching mode:*  Theoretical lesson plus laboratories in Python using Google Colab [https://colab.research.google.com/](https://colab.research.google.com/) *Program:* - Introduction to AI and ML - Trustworthy AI and ML - Reliable ML - Fair ML - Private ML - Interpretable/Explainable ML *References:* - L. Oneto, et al. Towards learning trustworthily, automatically, and with guarantees on graphs: an overview. Neurocomputing, 2022 - Winfield, A. F. et al. "Machine ethics: the design and governance of ethical AI and autonomous systems." Proceedings of the IEEE 107.3 (2019): 509-517. - Floridi, L. "Establishing the rules for building trustworthy AI." Nature Machine Intelligence 1.6 (2019): 261-262. - L. Oneto and S. Chiappa. Fairness in machine learning. Recent Trends in Learning From Data. Springer, 2020 - Biggio, B. and Roli F. "Wild patterns: Ten years after the rise of adversarial machine learning." Pattern Recognition 84 (2018): 317-331. - Guidotti, R. et al. "A survey of methods for explaining black box models." ACM computing surveys (CSUR) 51.5 (2018): 1-42. - Liu, B. et al. "When machine learning meets privacy: A survey and outlook." ACM Computing Surveys (CSUR) 54.2 (2021): 1-36.

01 - 01 January 2027

Interpretability and explainability in machine learning

Politecnico di Milano

Machine Learning is becoming ubiquitous and data-driven models are increasingly used to make high-stakes decisions in sensitive domains such as healthcare, safety systems, education, and criminal justice. Accordingly, it is important to ensure that decision-makers properly understand how these models work such that they can trust their outputs. The course will cover the following topics. Fundamentals: an overview of the field and seminal papers, the definition of interpretability and explainability, scope of interpretability, properties of explanations, evaluating interpretability. Interpretable Models: interpretability properties of linear regression, logistic regression, decision trees, rule-based techniques, generalized additive models, and instance-based approaches. Model-Agnostic Methods: partial dependence plot, individual conditional expectation, accumulated local effects plot, feature interaction, feature importance, Shapley additive explanations, local and global surrogates. Example-Based Explanations: counterfactual explanations, adversarial examples, prototypes, and influential instances Advanced Topics: Interpretability of Neural Networks and Deep Learning, interpretability and causality, fairness, debugging, human-in-the-loop approaches.

19 May 2026 - 04 June 2026

Ethics of artificial intelligence

Politecnico di Milano

This course examines today’s most pressing ethical issues related to Artificial Intelligence (AI) and explores ways to leverage technology for the benefit of mankind. It provides insights into how responsible innovation of technology could contribute to the quality of human life by combining a fair allocation of risks and benefits.

13 - 17 April 2026

Theory and practice of learning from data

University of Genoa Unit Genoa

TPLD (PhD)

This course aims at providing an introductory and unifying view of learning from data (inductive Artificial Intelligence). The course will present an overview of the theoretical background of learning from data, including the most used algorithms in the field, as well as  practical applications. Teaching mode:  Theoretical lesson plus laboratories in Python using Google Colab [https://colab.research.google.com/](https://colab.research.google.com/) Program: - Inference: induction, deduction, and abduction - Statistical inference - Machine Learning - Deep Learning (and Transfer Learning) - GenAI - Model selection and error estimation References: - C. C. Aggarwal "Data Mining - The textbook" 2015 - T. Hastie et. al "The Elements of Statistical Learning: Data Mining, Inference, and Prediction" 2009. - S. Shalev-Shwartz et. al "Understanding machine learning: From theory to algorithms" 2014 - C. M. Bishop et. al "Deep learning: Foundations and concepts" 2023 - D. Foster. "Generative deep learning". 2022. - L. Oneto "Model Selection and Error Estimation in a Nutshell" 2020

19 - 19 March 2026

Learning theory

Politecnico di Milano Unit Milan

Dott. - MI (1380) Ingegneria dell'Informazione / Information Technology

Provide PhD students in Information Technology with a complete overview of fundamental machine learning techniques that they may use during their research activities. Present the theoretical tools for analyzing the performance of machine learning algorithms. Discuss concrete examples of how these techniques can be applied to analyze widely adopted algorithms. The course will focus on both supervised learning and sequential decision-making.

06 March 2026 - 01 April 2026