9.520: Statistical Learning Theory and Applications, Fall 2014



Class Times: Monday and Wednesday: 1:00pm - 2:30pm
Units: 3-0-9 H,G
Location: 46-3189
Instructors:

Tomaso Poggio (TP), Lorenzo Rosasco (LR), Carlo Ciliberto (CC), Charlie Frogner (CF), Georgios Evangelopoulos (GE), Ben Deen (BD).

Office Hours: Friday 2-3 pm in 46-5156, CBCL lounge (by appointment)
Email Contact : 9.520@mit.edu
Previous Class: FALL 2013
Further Info: 9.520 is currently NOT using the Stellar system

Course description

The class covers foundations and recent advances of Machine Learning in the framework of Statistical Learning Theory.

Understanding intelligence and how to replicate it in machines is arguably one of the greatest problems in science. Learning, its principles and computational implementations, is at the very core of intelligence. During the last decade, for the first time, we have been able to develop artificial intelligence systems that can solve complex tasks previously considered out of reach. Modern cameras recognize faces, and smart phones voice commands, cars can see and detect pedestrians and ATM machines automatically read checks. The machine learning algorithms that are at the roots of these success stories are trained with labeled examples rather than programmed to solve a task. Among the approaches in modern machine learning, the course focus is on regularization techniques, that are key to high- dimensional supervised learning. Regularization methods allow to treat in a unified way a large number of diverse approaches, while providing tools to design new ones.

Starting from classical methods such as Regularization Networks and Support Vector Machines, the course covers state of the art techniques based on the concepts of geometry (aka manifold learning), sparsity and a variety of algorithms for supervised learning (batch and online), feature selection, structured prediction and multitask learning.

The final part of the course is new and will focus on connections between Radial Basis Functions and deep learning networks. We will also introduce new techniques for the (unsupervised) learning of data representation. In particular we will present a new theory (M-theory) of hierarchical architectures, motivated by the visual cortex, that might suggest how to learn, in an unsupervised way, data representation that can lower the sample complexity of a final supervised learning stage.

The goal of this class is to provide students with the knowledge needed to use and develop effective machine learning solutions to challenging problems.

Prerequisites

We will make extensive use of linear algebra, basic functional analysis (we cover the essentials in class and during the math-camp), basic concepts in probability theory and concentration of measure (also covered in class and during the mathcamp). Students are expected to be familiar with MATLAB.

Grading

Requirements for grading (other than attending lectures) are: 2 problems sets, and a final project.

Problem Sets

Instructions: Use the LaTeX template provided to report your work. You are allowed a maximum of ten pages. Do not change the font or margin of the template. Submit the writeup and code scripts in a (zip/tar) file named <LastName_FirstName>_9520_fall2014_pset1 via email to 9.520@mit.edu using as a subject line "[9.520 fall2014 pset1] LastName FirstName". You also have to submit a printed copy of the solutions (not the code!) in class by the due date.

Projects

Project abstract submission (Due: Nov. 12)
Project topics suggestions: pdf, g-docs

Project draft submission (Due: Dec. 08)

Wikipedia articles

The course project can be a Wikipedia entry (we encourage and recommend this) or an implementation/extension of GURLS. You should use the standard Wikipedia article format, follow Wikipedia layout, style and content rules and create Sandbox pages for experimenting and drafting your articles. Here is a list of previously created or edited wikipedia entries.

Syllabus

Follow the link for each class to find a detailed description, suggested readings, and class slides. Some of the later classes may be subject to reordering or rescheduling.

Class Date Title Instructor(s)


Reading List

There is no textbook for this course. All the required information will be presented in the slides associated with each class. The books/papers listed below are useful general reference reading, especially from the theoretical viewpoint. A list of suggested readings will also be provided separately for each class.

Primary References

Background Mathematics References

Neuroscience Related References