OVERVIEW

The goal of this course is to provide an overview of Machine Learning algorithms dealing with sequential/dynamic data and agents that can interact with the environment within the reinforcement learning framework.

AIMS AND CONTENT

LEARNING OUTCOMES

Learning how to use sequential and reinforcement learning algorithms by grasping the underlying computational and modeling issues.

AIMS AND LEARNING OUTCOMES

At the end of the course, students will be able to:

UNDERSTAND and use  machine learning algorithms and models for dynamic data and agents 

UNDERSTAND how to effectively set-up machine learning pipelines with dynamic data/agents

IMPLEMENT the learning algorithms presented in the course

DEVELOP the ability to critically analyze analytical results

PREREQUISITES

Basic probability, calculus, linear algebra, programming.

TEACHING METHODS

Theoretical classes might be complemented by practical lab sessions

SYLLABUS/CONTENT

The course will cover the following topics:

• Dynamical systems
• Time series
• Dynamic mode decomposition
• Neural netoworks for sequential data
• Reinforcement Learning 
• Multi-Arm Bandits
• Markov Decision Processes
• Prediction and Control
• Monte Carlo and Temporal Differences Methods

RECOMMENDED READING/BIBLIOGRAPHY

The material provided by the instructors (notes, papers, books), see the course Aulaweb page additional references.

TEACHERS AND EXAM BOARD

Exam Board

ALESSANDRO VERRI (President)

NICOLETTA NOCETI

LORENZO ROSASCO (President Substitute)

LESSONS

LESSONS START

In agreement with the calendar approved by the Degree Program Board of Computer Science.

Class schedule

The timetable for this course is available here: Portale EasyAcademy

EXAMS

EXAM DESCRIPTION

The exam will be a project and a discussion of the material presented in the course.

ASSESSMENT METHODS

The exam will evaluate the overall understanding of course material, the capability to generalize the concepts to unseen problems and analyze the obtained results.
Clarity of exposition, completeness of the concepts, quality of the proposed solutions and critical thinking will be taken into account.

Exam schedule