Lecture Notes for Machine Learning (308-766B)

All the lecture notes are available in PDF format and in postscript format (for easier viewing on the screen). The reader for PDF files is available free from Adobe for UNIX, Macs, and Windows. You can view both postscript and PDF files using ghostview. For printing convenience, a postscript format having 4 slides per page is also included (marked PS4).

Lec.
Date
Topic
Reading
Slides
1
 Jan. 3 
 Introduction. Machine learning problems.  Mitchell, Chapter 1  
2
 Jan. 8 
 Learning Boolean Concepts and Inductive Bias  Mitchell, Chapter 2  PDF  PS  PS4 
3
 Jan. 10 
 Computational learning theory
The PAC learning model.		  Mitchell, Sections 7.1-7.3  PDF  PS  PS4 
4
 Jan. 15 
 Decision Trees - Basics  Mitchell, Chapter 3  PDF  PS  PS4 
-
 Jan. 17 
 No lecture    
5
 Jan. 22 
 Decision Trees - Details  Mitchell, Chapter 3  PDF  PS  PS4 
6
 Jan. 24 
 Artificial Neural Networks
Perceptron, Gradient Descent, Backpropagation		  Mitchell, Chapter 4  PDF  PS  PS4 
-
 Jan. 17 
 No lecture    
7
 Jan. 31 
 Artificial Neural Networks
Variations, RBF Networks, VC Dimension		  Mitchell, Chapter 4 and section 7.4  PDF  PS  PS4 
8
 Feb. 5 
 Artificial Neural Networks
More on VC Dimension. Sparse Distributed Memories		  Mitchell, Section 7.4.
P. Kanerva (1993). Sparse Distributed Memory and Related Models.		  PDF  PS  PS4 
17
 Mar. 14 
 Reinforcement Learning
Introduction		  Mitchell, Section 7.4.
P. Kanerva (1993). Sparse Distributed Memory and Related Models.		  PDF  PS  PS4 

Lecture 12: Bayesian Learning Monday, February 26. Postscript format
Associated reading: Mitchell, Sections 6.1-6.10.

Lecture 13: Naive Bayes Learning. Instance-Based Learning Wednesday, February 28. Postscript format
Associated reading: Mitchell, Chapter 8.

Lectures 14 and 15: Support Vector Machines

Doina PRECUP
Last modified: Mon Mar 19 12:08:43 EST 2001