OVERVIEW

This course deals with fundamental concepts and advanced methods on the design of machine learning systems, security of machine learning, trustworthy artificial intelligence, and their applications to pattern recognition. During the course students will deepen the international regulations on "Trustworthy AI" and the main techniques for designing and applying machine learning algorithms with robustness, fairness, privacy preserving, and explainable AI. The course is enriched with the presentation of various industrial, management and economics case studies.

AIMS AND CONTENT

LEARNING OUTCOMES

The course presents the advanced concepts behind the use of Artificial Intelligence for predictive and prescriptive modeling. During the course students will deepen the international regulations on "Trustworthy AI" and the main techniques for designing and applying machine learning algorithms with robustness, fairness, privacy preserving, and explainability properties. The course is enriched with the presentation of various industrial, management and economics case studies.

AIMS AND LEARNING OUTCOMES

Understanding of fundamental concepts and advanced methods on the design of machine learning systems, security of machine learning, trustworthy artificial intelligence and their applications to pattern recognition. Ability to answer open-ended questions with closed books, solve numerical exercises, use open-source libraries for the design of machine learning systems.

PREREQUISITES

This course is for graduate students who already attended basic courses (or have a basic/intermediate knowledge) of machine learning and artificial intelligence and have a basic/intermediate knowledge of programming languages (in particular, the Python language).

TEACHING METHODS

Lectures. The lecturer will use slides. Copies of slides will be provided to the students. Hands-on classes on design of machine learning systems.

SYLLABUS/CONTENT

1. Introduction to machine learning systems: overview of machine learning systems; when to use machine learning in industry and business.
2. Machine Learning Use Cases: machine learning in research and in production; machine learning versus traditional software systems.
3. Machine Learning Systems Design: requirements, data engineering, feature engineering, training, labelling, data augmentation, model development and evaluation, continual learning, monitoring and test in production.
4. Security of Machine Learning: attacks and defenses for machine learning
5. Explainable AI: explainability methods. Global and local methods. Model-specific and model-agnostic methods.
6. Fairness and privacy of machine learning:  fairness and privacy-related threats and defenses.
7. AI regulations: the European AI Act.  European ethics guidelines for trustworthy AI. AI regulations in the world.
8. Practical sessions. Hands-on classes on design of machine learning systems.

RECOMMENDED READING/BIBLIOGRAPHY

• Chip Huyen, Designing Machine Learning Systems, O’Reilly, 2022
• A. Joseph, B. Nelson, B. Rubinstein, D. Tygar, Adversarial machine learning, Cambridge University Press, 2018

TEACHERS AND EXAM BOARD

Exam Board

LUCA DEMETRIO (President)

LUCA ONETO (President)

FABIO ROLI (President)

LESSONS

LESSONS START

See the official calendar of the University of Genova.

EXAMS

EXAM DESCRIPTION

Intermediate in class assignments or home assignment+oral exam.

ASSESSMENT METHODS

Intermediate in class assignments (closed-book solutions of numerical/coding exercises and open-ended/closed questions), or home assignment+oral exam. Grading policy = open/closed questions (15/30) +  numerical/coding exercises (15/30)

Exam schedule

FURTHER INFORMATION

Contact the instructor by email.