Mathematical Tools in Machine Learning
Autumn semester 2019
General information
Lecturer  Fadoua Balabdaoui 

Assistants  Loris Michel 
Lectures  Thu 1012 HG E 5 
Course catalogue data  >> 
Course content
In the exploding world of artifical intelligence and automated learning, there is an urgent need to go back to the basis of what is driving many of the wellestablsihed methods in statistical learning. The students attending the lectures will get acquainted with the main theoretical results needed to establish the theory of statistical learning. We start with defining what is meant by learning a task, a training sample, the tradeoff between choosing a big class of functions (hypotheses) to learn the task and the difficulty of estimating the unknown function (generating the observed sample). The course will also cover the notion of learnability and the conditions under which it is possible to learn a task. In a second part, the lectures will cover algoritmic apsects where some wellknown algorithms will be described and their convergence proved. Through the exerices classes, the students will deepen their understanding using their knowledge of the learned theory on some new situations, examples or some counterexamples.
Announcements
 For phd students who want to get credits for this course, the requirement is to submit solutions of 3 problem sets out of 4
 Question hours before exam: 21.01.20: room HG G 19.1 at 16:00, 30.01.20: room LEE C 104 at 16:00
Course materials
Week  Topic  

Week 1 


Week 2 


Week 3  Exercise session 1

Solutions 
Week 4 


Week 5 


Week 6  Exercise session 2

Solutions 
Week 7 


Week 8 


Week 9  Exercise session 3

Solutions 
Week 10 


Week 11 


Week 12 


Week 13  Exercise session 4

Solutions 
Exercise classes
Series
Exercises  Solutions  

Series 1  Solutions 1  TBA 
Literature
 Anthony, M. and Bartlett, P.L., 2009. Neural network learning: Theoretical foundations. Cambridge university press
 Lecture Notes of Philippe Rigollet On Mathematics of Machine Learning
Main reference:
ShalevShwartz, S. and BenDavid, S., 2014. Understanding machine learning: From theory to algorithms. Cambridge university press
Additional references: