Autonomous and Adaptive Systems - M

The course is included  in the second cycle degree programme (LM) in Artificial Intelligence (cod. 9063), and it is also valid for second cycle degree programme (LM) in Computer Engineering (cod. 5826).

For more detailed informations refer to the course page Autonomous and Adaptive Systems M 2022/2023 — University of Bologna (unibo.it)

Course overview

Purpose

The primary objective of this course is to furnish an extensive insight into the intricacies involved in devising autonomous and adaptable computing systems, both from a theoretical and practical standpoint. Encompassing a vast array of topics, including the fundamental principles of autonomous system design, reinforcement learning, game-theoretic approaches to cooperation and coordination, bio-inspired systems, complex adaptive systems, and computational social systems, this module strives to provide an all-encompassing understanding of the subject matter. Additionally, the module delves into the practical applications of these concepts across diverse fields, such as distributed and networked systems, mobile and ubiquitous systems, robotic systems, and vehicular and transportation system.

Contents

The course syllabus encompasses an introduction to the design principles of adaptive and autonomous systems, including intelligent agents and machines, alongside a comprehensive review of the fundamental aspects of Machine Learning (ML) and Deep Learning (DL). Additionally, the curriculum introduces Reinforcement Learning (RL), covering multi-armed bandits, Montecarlo methods, tabular methods, approximation function methods, and deep RL. The course also explores the applications of RL in game theory, classic control theory, and robotics, while considering its significance in cognitive sciences and neuroscience. The curriculum further scrutinizes the relationship between intelligent machines and creativity, focusing on Generative Deep Learning, AI and the Arts. Other notable subjects of study include models of human, artificial, and hybrid societies, algorithmic game theory, and AI-based decision-making processes such as cooperation, coordination, social dilemmas, and Multi-Agent Reinforcement Learning. The course also encompasses bio-inspired adaptive systems, autonomous and mobile robots, driverless cars, and autonomous transportation systems, while delving into the ethical implications of AI and autonomous systems. Finally, the syllabus touches upon critical themes such as machine intelligence, super-intelligence, self-awareness, controllability, and the future of AI. The course provides opportunities for hands-on experience through laboratory sessions designed to discuss practical aspects of the techniques and methodologies taught in the class.

All the lectures material and files (slides, exercises and solutions, suggested additional exercises, examples, project proposals, ...) are available in the section courses on Mirco Musolesi 's website.

Timetable

Typically classes are held in the second semester, from February to June. For more information please refer to page:  Course Timetable — Artificial intelligence - Laurea Magistrale - Bologna (unibo.it)