Ceit home

Home

Advanced Topics in Learning Theory

 

 

Instructors:

  • Dr. Saeed Shiry

  • Elham Bavafa

 

Winter 2011

Syllabus
Homework
Presentations
Exam
Projects 
Link
Machine learning refers to a system capable of the autonomous acquisition and integration of knowledge. The primary objective of this course is to provide a broad introduction to machine learning, including discussions of the major approaches, basic principles, techniques, and applications of machine learning. The course gives the student the basic ideas and intuition behind modern machine learning methods as well as a bit more formal understanding of how and why they work.

Method:

The course consists of

  • Lectures with discussions,

  • Homework assignments,

  • Reading assignments,

  • final exam,

  • Project 

This is a research oriented course, intended first to bring the students to the state of the art, and then to help them do a project and paper of publishable quality. 

Prerequisites

 

Reading Material: 

  1.  Statistical Learning Theory By Valdimir Vapnik 1998

  2. The Nature of Statistical Learning Theory ,Vladimir N. Vapnik, 2000,

  3. Learning with Kernels, Bernhard Scholkopf, 2002

  4. Modern Multivariate Statistical Techniques, Alan Julian Izenman,2008

  5.  Advances in Learning Theory: Methods, Models and Applications Edited by J.A.K. Suykens ,G. Horvath ,S. Basu C. Micchelli ,J. Vandewalle ,2003


 

Research papers

Online resources

 

Course Evaluation: 

Homework      

Final                 

Project             

Presentation

Syllabus
References Chapter Slide Document Date
Introduction
Regularization
Computational learning Theory

Consistency of Learning Processes

2 2 Keywanrad 7/10

Bounds on the Rate of Convergence of
Learning Processes

2 3 PoorMohammad 7/17

Controlling the Generalization Ability of
Learning Processes

2 4 Rezvanian 7/24

 Methods of Pattern Recognition

1,2,3 5 Zojaji 8/1

 

           

Methods of Function Estimation

2,3   Shoaleh   8/15

Regularization 3 4 Sadat/Khosravani   8/22

ICA 4   PoorMohammad   8/29

Bayesian Kernel Methods 3 17 Keywanrad    9/6

 Manifold 3 15 Sadat 9/13
Project Presentation     Zojaji/Rezvanian/Khosravani   9/20
Project Presentation
 
  Sholeh/Poormohammad   9/27
Project Presentation     Sadat/Keywanrad   10/4
             
             

  دانشجویان گرامی باید هر هفته گزارشی حداقل 5 صفحه ای به زبان فارسی در مورد پیشرفت پروژه انتخابی خود را تحویل خانم باوفا بدهند. این گزارش باید تا آخر روز 5 شنبه هر هفته ایمیل شده باشد. اولین گزارش 12 آبان ماه ارسال شود.

  Presentations  

 

کتاب درس

کتاب درس

مرجع 4

کتاب اس وی ام

Homework

 

29 شهریور

HW1

تمرین اول

 
     
   

 

Exam

 

 
Projects

 

 

Link  
Course Email: shiry-at-aut.ac.ir
 
Last update: 13/09/2011