**Fabio Aiolli**

Department of Mathematics, University of Padova

email: aiolli[at]math.unipd.it

**SSD:**

INF/01

**Aim:**

The aim of the course is to introduce the student to the basic concepts that characterize machine learning, i.e. the class of techniques and algorithms that starting from empirical data allow a computer system to acquire new knowledge, or to correct and/or to refine knowledge already available. These techniques are particularly useful for problems for which it is impossible or very difficult to reach a mathematical formalization usable for the definition of an ad hoc algorithmic solution. Examples of these problems are perceptual tasks, such as visual recognition of handwritten digits, or problems in which data is corrupted by noise or is incomplete

**Course contents:**

The course provides a broad introduction to machine learning. Topics include: supervised learning (generative/discriminative learning, parametric/non parametric learning, neural networks, support vector machines); unsupervised learning (flat and hierarchical clustering); learning theory (bias/variance tradeoffs; VC theory; large margins).

**Syllabus:**

1. Introduction: when machine learning is useful; machine learning paradigms; basic ingredients of machine learning

2. Supervised Learning (SL): Concept Learning, Decision Trees, Probabilistic Learning, Neural Networks and Support Vector Machines. Learning Theory. The Representation problem. Evaluation measures

3. Unsupervised Learning (UL): Flat and Hierarchical Clustering. Evaluation measures

**Course requirements:**

The student should be familiar with basic concepts in probability and calculus of multivariate functions. It is also advisable to have basic knowledge of programming

**Examination and grading (if foreseen):**

The students will be evaluated on an oral presentation on one of the topics covered in the course

**Schedule:**

22 June, 15.00-17.00, meeting Room, HIT centre via Luzzatti 4

24 June, 15.00-17.00, meeting Room, HIT centre via Luzzatti 4

27 June, 15.00-17.00, meeting Room, HIT centre via Luzzatti 4

29 June, 15.00-17.00, meeting Room, HIT centre via Luzzatti 4

01 July, 15.00-17.00, meeting Room, HIT centre via Luzzatti 4