Machine Learning (CS)

General information

Degree: Master in Computer Science
Period: September - December

Objectives

Provide knowledge of both theoretical and practical aspects of machine learning. Present the main techniques of machine learning and probabilistic reasoning.

Prerequisites

Linear algebra, probability theory (briefly revised during the course). Boolean algebra, knowledge of a programming language. For a good introduction to linear algebra see: Gilber Strang, Introduction to Linear Algebra, Wellesley-Cambridge Press, 2016.

Content

Introduction to machine learning: designing a machine learning system, learning settings and tasks, decision trees, k-nearest-neighbour estimation. Mathematical foundations: linear algebra, probability theory, statistical tests. Bayesian decision theory, maximum likelihood and Bayesian parameter estimation. Probabilistic graphical models, inference, parameters and structure learning. Discriminative learning: linear discriminant functions, support vector machines, kernels for vectorial and structured data. Neural networks: representation learning, deep architectures.

Mode

Teaching for this course is in blended mode.

  • Students enrolled in the first year of the Master in Computer Science (LM Informatica) can physically attend the course (room b107).
  • All other students should follow remotely. The details of the Zoom meeting have been already communicated, and are now available on the Moodle community.

Course Information

Instructor: Andrea Passerini
Email:
Teaching assistant: Giovanni Pellegrini
Email: giovanni.pellegrini@unitn.it
Office hours: Arrange by email
Lecture time: Tuesday 9:30-11:30
Thursday 9:30-11:30
Lab time and place: TBD
Communications: Please check the moodle page of the course for news and updates.
Bibliography: R.O. Duda, P.E. Hart and D.G. Stork, Pattern Classification (2nd edition), Wiley-Interscience, 2001.
D. Koller and N. Friedman, Probabilistic Graphical Models, The MIT Press, 2009
J.Shawe-Taylor and N. Cristianini, Kernel Methods for Pattern Analysis, Cambridge University Press, 2004.
I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, The MIT Press, 2016 (online version available here).
Slides: Introduction [slides] [handouts]
Decision Trees [slides] [handouts]
K-nearest neighbours [slides] [handouts]
Linear algebra [slides] [handouts]
Probability theory [slides] [handouts]
Evaluation [slides] [handouts]
Bayesian decision theory [slides] [handouts]
Parameter estimation [slides] [handouts]
Bayesian Networks [slides] [handouts]
Inference in BN [slides] [handouts]
Learning BN [slides] [handouts]
Naive Bayes [slides] [handouts]
Bayesian Network lab [slides] [data] [software]
Linear discriminant functions [slides] [handouts]
Support Vector Machines [slides] [handouts]
Non-linear Support Vector Machines [slides] [handouts]
Kernel Machines [slides] [handouts]
Scikit-learn lab [slides] [material]
Deep Networks [slides] [handouts]
Deep Network lab [slides] [material]
Clustering [slides] [handouts]
Videos: Registered lectures made available on Moodle (on a weekly basis)

Exams

Modality: Oral examination.