Reading by Syllabus Topic

Listed below are the relevant sections of the recommended reading and the supplemental readings for various topics of the course. It is expected that you will need to read at least one piece of supportive material for each topic.

Introduction(Lectures 1):

Weiss and Kulikowski (WK) Chapter 1.

Bayesian Decision and Classification(Lectures 2,3,4):

Probability theory handout, WK Chapter 3.

Learning theory I: validation(Lecture 5):

WK Chapter 2.

Learning theory II: Generalisation(Lecture 6):

none

Single-Layer Neural Networks (Lectures 7,8):

Perceptrons handout; WK Chapter 4.

Multi-Layer Neural Networks (Lectures 9 - 11):

Backpropagation handout; WK Chapter 4.

Learning from Non-numeric Data(Lectures 12 - 14:

Information theory handout, WK Chapter 5.

Non-symbolic Search Techniques(Lectures 15, 16):

Handouts.

Genetic Algorithms(Lectures 17, 18):

Genetic Algorithms handout.

Unsupervised learning(Lectures 19 - 21):

Unsupervised learning handout.