|SCIENTIFIC DISCIPLINARY SECTOR||MAT/06|
The course offers an introduction to the main machine learning algorithms, by covering the modeling and computational aspects.
The primary objective is to provide the students with the basic language and tools of machine learning, with particular emphasis on the supervised case. The approach is based on a formulation of the problem of machine learning as an inverse stochastic problem. The students will also need to know some of the best known algorithms, including both statistical and computational properties.
At the end of the course, the student will have:
Calculus for functions of sesveral variables, probability and linear algebra.
Classes using blackboard and lab activities
The course 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.
Hastie, Tibshirani and Friedman. Elements of statistical learning
Shalev-Shwartz and Ben-David. Understanding Machine Learning: from Theory to Algorithms
Office hours: By appointment wich can be fixed in person or via email : email@example.com
SILVIA VILLA (President)
LORENZO ROSASCO (President Substitute)
ERNESTO DE VITO (Substitute)
In agreement with the offical academic calendar
To pass the exam the student have to present a short report. The student can choose one among the following options:
The topic studied in the report must be decided in advance in agreement with the instructors.
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.
The report preparation and its discussion are aimed at verifying the student's achievement of an independent critical reasoning capability in the context of machine learning.
During the report presentation, basic questions d on the topics covered by the course amy be asked.