Machine Learning Crash Course

Instructors
Lorenzo Rosasco Lorenzo.rosasco@unige.it

Hours and Credits
Total of 24h 8 Credits

Synopsis
This course provides an introduction to the fundamental methods at the core of modern Machine Learning. It covers theoretical foundations as well as essential algorithms. Classes on theoretical and algorithmic aspects are complemented by practical lab sessions.

Tools used:

Hardware
Laptop with Matlab (optional)

Software
Matlab

Syllabus
Local Methods and Model Selection
Laboratory - Local Methods for Classification
Local Methods and Model Selection
Laboratory - Local Methods for Classification
Regularization Networks I: Linear Models
Dimensionality Reduction and PCA
Variable Selection and Sparsity
Laboratory - PCA and Sparsity
Clustering
Applications of Machine Learning
Talks by industrial partners

Final exam
There will be a final examination decided by the instructors.


Prerequisites
Bare fundamentals in Calculus and Linear Algebra. The rest of the mathematical tools needed for the course will be covered in class. This introductory course is suitable for undergraduate/graduate students, as well as professionals.

Reading List
References
- L. Rosasco. Introductory Machine Learning Notes.
Further readings
- T. Poggio and S. Smale. The Mathematics of Learning: Dealing with Data. Notices of the AMS, 2003
- Pedro Domingos. A few useful things to know about machine
learning. Communications of the ACM CACM Homepage archive. Volume 55 Issue 10, October 2012 Pages 78-87.
PhD Program in Bioengineering and Robotics – 2016-2017
- T. Hastie, R. Tibshirani, and J. Friedman. The Elements of Statistical Learning:
Prediction, Inference and Data Mining. Second Edition, Springer Verlag, 2009
(available for free from the author's website).

Useful Links
MIT 9.520: Statistical Learning Theory and Applications, Fall 2013
(http://www.mit.edu/~9.520/).
- Stanford CS229 Machine Learning Autumn 2013 (http://cs229.stanford.edu). See also the Coursera version (https://www.coursera.org/course/ml).

Venue
Department of Informatics Bioengineering Robotics and Systems Engineering (DIBRIS)

Università degli Studi di Genova - Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi Via Dodecaneso, 35, 16146 Genova, Italy.
https://goo.gl/maps/2ydsnFJcC1J2

Accomodations:
http://lcsl.mit.edu/courses/common_data/hotels.pdf

Course dates
26 – 30 June 2017