OVERVIEW

The teaching  offers an introduction to the main machine learning algorithms, by covering the modeling and computational aspects.

AIMS AND CONTENT

LEARNING OUTCOMES

Provide the tools for theoretical understanding and practical use of the main supervised and unsupervised learning algorithms.

AIMS AND LEARNING OUTCOMES

At the end of the course, the student will have:

• a good understanding of the basic notions of machine learning and of the related basic mathematical tools; 
• a comprehension  of the basic concepts and techniques of convex optimization
• a good knowledge of the statistical and computational  properties of some well known machine learning   algorithms;
• some ability to implement machine learning algorithms on synthetic and real data sets.

PREREQUISITES

Calculus for functions of sesveral variables, probability and linear algebra. 

TEACHING METHODS

Classes using  blackboard  to introduce the theorethical concepts and the main statistical learning algorithms. Lab activities in parallel to experience how the proposed methods work in practce.

SYLLABUS/CONTENT

The teaching will offer an introduction to the main tools which are necessary to understand statistical learning,  and a number of supervised learning algorithms, such as local methods, regularization networks, linear and non linear models. The Course will also give a basic introduction to neural networks. Unsupervised problems such as clustering and dimensionality reduction will also be treated.  All the methods covered in the course will be implemented and during the lab sessions. 

The teaching will contribute to the following objectives and goals for the  Agenda 2030 for sustainable development:

• Goal 4. Ensure inclusive and equitable quality education and promote lifelong learning opportunities for all
• Goal 5. Achieve gender equality and empower all women and girls

RECOMMENDED READING/BIBLIOGRAPHY

• L. Rosasco, Introductory Machine Learning Notes, University of Genoa,  (http://lcsl.mit.edu/courses/ml/1718/MLNotes.pdf)
• Steinwart, Ingo, Christmann, Andreas, Support vector machines, Springer, ISBN 978-0-387-77241-7
• Cucker, Felipe, Zhou, Ding-Xuan, Learning theory: an approximation theory viewpoint, Cambridge University Press 2007, ISBN  978-0-521-86559-3

• Hastie, Tibshirani and Friedman. Elements of statistical learning

• Shalev-Shwartz and Ben-David. Understanding Machine Learning: from Theory to Algorithms

• Boyd, Vandenberghe, Convex Optimization, Cambridge University Press, 2004, ISBN 0 521 83378 7

TEACHERS AND EXAM BOARD

Exam Board

SILVIA VILLA (President)

CESARE MOLINARI

LORENZO ROSASCO (President Substitute)

ERNESTO DE VITO (Substitute)

LESSONS

LESSONS START

In agreement with the offical academic calendar

EXAMS

EXAM DESCRIPTION

To pass the exam the student has two options: 

1) participate to intermediate written and lab verifications. At the end of the teaching, the student may decide to take an oral exam to improve her/his mark.

2) participate to an oral exam at the end of the teaching on the entire content of the course. ​

Students with DSA certification ("specific learning disabilities"), disability or other special educational needs are advised to contact the teacher at the beginning of the course to agree on teaching and examination methods that, in compliance with the teaching objectives, take account of individual learning arrangements and provide appropriate compensatory tools.

ASSESSMENT METHODS

The written  and the oral exam contain exercises and theoretical questions on the topics covered by the teaching, and will require the comprehension and the ability to use the introduced concepts and algorithms. The lab exam will be a guided  implementation and  use of the algorithms introduced in theoretical classes (notebooks will be used). 

Exam schedule