198:536 Machine Learning

Spring 2007

 

Instructor: Dr. Ahmed Elgammal -- email: elgammal at cs

Class Time: Monday 6:40-9:30 pm Hill 254

Office hours: Tuesday 4:30-6:30pm

 

TA: Nishkam Ravi Email: nravi at cs

TA office hours: Tuesday 4-6pm Core 334

 

Class Web page: http://www.cs.rutgers.edu/~elgammal/cs536.html

 

Class Calendar and Lecture Slides

 

 

Overview:

This is a basic graduate-level Machine Learning class that intends to cover a variety of fundamental Machine Learning topics to get you acquainted with the field and its applications.

Topics:

 

This is not a comprehensive list of topics nor it reflects the order we will present the topics. Its more a highlevel abstraction of the topics:

 

Basics: Whats machine learning, dealing with data, Concept Learning, Version Spaces.

Linear Models: Linear Regression, Nave Bayes

Nonlinear Models: Neural Networks, Instant Based Learning, Decision Trees, Boosting, MDL.

Margin-based Approaches: Support Vector Machines and Kernels Methods

Learning theory: VC dimension, PAC learning, Error Bounds

Unsupervised Learning: Clustering, K-means, Expectation Maximization, dimensionality Reduction.

Structured Models: Graphical Models, Hidden Markov Models.

Reinforcement Learning and Evolutionary Learning.

Recommended Background:

Linear algebra and basic probability and statistics.

Textbooks

 

General Machine Learning text books:

 

Introduction to Machine Learning, Ethem Alpaydin- MIT press 2004 

 

Machine Learning, Tom Mitchell. 1997

 

Pattern Recognition and Machine Learning, Christopher M. Bishop, Springer 2006

 

Pattern Classification (2nd Edition), Duda, Hart and Stork., Wiley 2001

 

Topic-Oriented text books:

Learning With Kernels, Bernhard Scholkopf and Alexaner J. Smola

An Introduction To Genetic Algorithms, Melanie Mitchell

Neural Networks for Pattern Recognition, Chris Bishop.

Principle of Data Mining, Hand Mannila, and Smyth

Course Load

 


Class Project:

Students (in groups of 2 or indviduals) are expected to work on a class research project throughout the semester to explore a recent Machine Learning research topic. Students are to choose their own projects and are encouraged to find a project related to their own research. The project ideas are expected to be innovative, experimental and feasible to be done within the semester time frames.

 

Project time line (tentative- to be modified)