Università di Pavia - Offerta formativa

MACHINE LEARNING

Anno immatricolazione

2020/2021

Anno offerta

2020/2021

Normativa

DM270

SSD

ING-INF/05 (SISTEMI DI ELABORAZIONE DELLE INFORMAZIONI)

Dipartimento

DIPARTIMENTO DI MATEMATICA 'FELICE CASORATI'

Corso di studio

MATEMATICA

Curriculum

PERCORSO COMUNE

Anno di corso

1°

Periodo didattico

Secondo Semestre (01/03/2021 - 11/06/2021)

Crediti

6

Ore

59 ore di attività frontale

Lingua insegnamento

English

Tipo esame

ORALE

Docente

CUSANO CLAUDIO (titolare) - 6 CFU

Prerequisiti

Students are expected to have a basic knowledge of linear algebra, vector calculus, probability and statistics. They are also expected to be able to design and write simple computer programs.

Obiettivi formativi

At the end of the course students will be able to understand and discuss the principles of machine learning. They will be able to analyze a problem, and to design and implement a solution. They will be familiar with the most important techniques in the field and will be able to use them to build machine learning systems by using the Python programming language.

Programma e contenuti

After a general introduction to machine learning, the first lectures will focus on the main techniques used to tackle the problem of classification by supervised learning. More in detail the following topics will be presented:

- logistic regression;

- generalization and regularization;

- the perceptron algorithm;

- linear and non-linear Support Vector Machines;

- multi-class models;

- cross validation and model selection;

- generative models and naive Bayes.

Artificial neural networks will be the main topic of the second part of the course. The lectures will cover:

- the biological inspiration;

- feed forward networks;

- the backpropagation algorithm;

- introduction to deep learning;

- convolutional neural networks;

- recurrent networks.

The last part of the course will present some application domains in which machine learning models are widely used:

- document classification;

- audio processing;

- image recognition.

- logistic regression;

- generalization and regularization;

- the perceptron algorithm;

- linear and non-linear Support Vector Machines;

- multi-class models;

- cross validation and model selection;

- generative models and naive Bayes.

Artificial neural networks will be the main topic of the second part of the course. The lectures will cover:

- the biological inspiration;

- feed forward networks;

- the backpropagation algorithm;

- introduction to deep learning;

- convolutional neural networks;

- recurrent networks.

The last part of the course will present some application domains in which machine learning models are widely used:

- document classification;

- audio processing;

- image recognition.

Metodi didattici

About two thirds of the course will be given as lectures in which machine learning principles and techniques will be illustrated, even through the presentation of case studies. One third of the course will take place in a laboratory, in which the students will learn to solve machine learning problems by using the Python programming language.

Testi di riferimento

The course is based on a set of notes that are supplemented by a selection of articles.

Modalità verifica apprendimento

The exam consists of an interview in which the student will discuss the topics of the course. During the interview the students will be asked to present their implementation of a solution for a specific machine learning problem.

Altre informazioni

Obiettivi Agenda 2030 per lo sviluppo sostenibile