78778 - Intelligent Systems M

Course Unit Page

SDGs

This teaching activity contributes to the achievement of the Sustainable Development Goals of the UN 2030 Agenda.

Affordable and clean energy Industry, innovation and infrastructure Sustainable cities

Academic Year 2021/2022

Learning outcomes

At the end of the course the students are able to use the main AI techniques to develop tools for solving real life applications. The students are able to understand and apply a wide range of techniques such as constraint programming, symbolic and sub-symbolic machine learning techniques, planning and swarm intelligence.

Course contents

PLANNING

  • Non-linear planning
  • Conditional planning 
  • Graph-based planning
  • Planning for robotics

MACHINE LEARNING: symbolic and sub-symbolic approaches

  • Decision trees - random forests
  • Neural networks
  • Bayesian approaches
  • Inductive logic programming

OPTIMIZATION

  • Constraint Programming and Global constraints
  • Search strategies
  • Applications

SWARM INTELLIGENCE

  • Ant colony
  • Bee Colony
  • Particle Swarm Optimization

Readings/Bibliography

S. J. Russel, P. Norvig: "Artificial Intelligence: A modern approach", Prentice Hall International. Execrises on-line [http://aima.cs.berkeley.edu/] .

M.Ginsberg: "Essentials of Artificial Intelligence", Morgan Kaufman,1993.

P. H. Winston: "Artificial Intelligence: Third Edition", Addison-Wesley, 1992.

Teaching methods

Lectures and laboratory exercises

Assessment methods

Written exam

Teaching tools

Slides of lectures

Tools in lab

Office hours

See the website of Michela Milano