Prof. Alessandro Sperduti,, Department of Mathematics
Course requirements: 
The student should have passed the exam of the course "Introduction to Machine Learning", or any other equivalent course
Examination and grading: 
The students will be evaluated on an oral presentation on one of the topics covered in the course
The aim of the course is to introduce state-of-the-art methods in machine learning, mainly considering kernel methods and deep learning techniques, and their application to different domains 

Course contents: 
The amount of data available in electronic format is increasing at such a rapid pace that intelligent automatic techniques for extraction of relevant information are gaining more and more importance. Machine Learning constitutes one of the main areas that contribute to the development of these techniques. In this course, we focus on two specific approaches: Kernel Methods and Deep Learning. Both traditional methods dealing with vectorial information and approaches able to directly deal with structured data will be presented. Finally, examples of applications will be discussed. 


1. Introduction
2. Statistical Learning Theory
 and Kernel Methods
3. Neural Networks and Deep Learning
4. Software resources and application examples 
5. Future Directions

11 July 2016, 10:00-13:00, HIT centre meeting room via Luzzatti 4
12 July 2016, 10:00-13:00, HIT centre meeting room via Luzzatti 4
21 July 2016, 10:00-13:00, HIT centre meeting room via Luzzatti 4
25 July 2016, 8:30-10:30, HIT centre meeting room via Luzzatti 4