FOUNDATIONS OF MACHINE LEARNING

The course aims at introducing the student to the principles, the algorithms and the main applications of Artificial Intelligence, with a focus on inference, machine learning and pattern recognition.

1. Knowledge and understanding
1.1. acquire the main models and algorithms of machine learning and pattern recognition

2. Ability to apply knowledge and understanding
2.1. acquire the ability to apply the studied models to real problems;
2.2. acquire the ability to critically assess the performance and the behavior of a model applied to a concrete problem

3. Judgement
3.1. ability to understand which characteristics of the various models of artificial intelligence are best suited to a given problem;
3.2. ability to critically evaluate the theoretical characteristics of the proposed models;

The student is expected to be familiar with the basic concepts of calculus and probability theory.

Information theory and inference: source coding, channel coding.

Learning and inference in neural networks: feed-forward networks, deep learning and related models.

Statistical learning theory, support vector machines, and kernel methods.

Unsupervised and semi-supervised learning: K-means, spectral clustering, dominant sets, game-theoretic models.

D. J. C. MacKay. Information Theory, Inference, and Learning Algorithms. Cambridge University Press, 2003.

I. Goodfellow, Y. Bengio and A. Courville. Deep Learning, MIT Press, 2016.

The exam consists of an oral test. The questions asked in the oral exam might cover all topics discussed in the class.

oral

The grading scale is established as follows:

A. Scores in the range 18–22 will be awarded in the presence of sufficient knowledge of the program.

B. Scores in the range 23–26 will be awarded in the presence of good knowledge of the program.

C. Scores in the range 27–30 will be awarded in the presence of excellent knowledge of all the topics covered in the program.

Honors will be awarded in the case of a perfect exam accompanied by a brilliant oral presentation.

Powerpoint presentations and chalk talk.