CS 420: Advanced Topics in Machine Intelligence
Spring 1995: Neural Networks

Instructor:
Bruce MacLennan
Phone: 974-5067
Office: 110-A Ayres
Hours: 2:30-3:25 or make an appointment
Email: maclennan@cs.utk.edu

Teaching Assistant:
Michael Christian
Phone: 4-8990
Office: 6, Ayres Hall
Hours: 10:00-12:00 in Hydra Lab
Email: christia@cs.utk.edu

Classes: 1:25-2:15 MWF (Ayres 125 - change from scheduled!)

Directory of Handouts, Labs, etc.

PDP Directory

Information

Description

CS 420 covers advanced topics in machine intelligence with an emphasis on faculty research. In the Spring semester of 1995 the topic will be neural networks, which is a promising, new approach to many AI problems, including knowledge representation, learning, pattern recognition, robotic control, natural language understanding and inference.

The course will begin with an overview of some topics in cognitive science, which will help students understand the differences between human and machine cognition. Characteristics of biological neural networks and the structure of the brain will be explained briefly so that their relation to artificial nerual nets is clearer. The course will then cover the principal neural net architectures and learning algorithms, including Hebbian learning and back-propagation. It will conclude with an exploration of future directions in neural net research, including specialized hardware implementations.

Prerequisites

Basic calculus through differential equations (Mat 231, 241), linear algebra (Mat 251), probability and statistics (Mat 222). Ability to program in Lisp (e.g. from CS 320).

Laboratories

There will be a number of labs in which students will get hands-on experience in designing neural nets to solve some simple problems. Most labs will involve using existing neural net simulators, though some projects will be programmmed in Common Lisp.

Text

Judith Dayhoff: Neural Network Architectures: An Introduction, Van Nostrand Reinhold, New York, 1990.

Tentative List of Topics

  1. Human Learning
  2. Introduction to Artificial Neural Nets
  3. Early Adaptive Networks
  4. Hopfield Networks
  5. Back-propagation
  6. BP Applications
  7. Competitive Learning & Lateral Inhibition
  8. The Brain and Biological Neurons
  9. Gabor Representations in Vision
  10. Biological Synapses
  11. Linear Systems Analysis of Dendritic Processes
  12. Kohonen Feature Map
  13. Neural Nets and Linear Regression
  14. Counterpropagation
  15. Applications and Future Directions
Return to MacLennan's home page

Send mail to Bruce MacLennan / MacLennan@cs.utk.edu