EE 4745: Neural Computing

http://www.ece.lsu.edu/jxr/4745 Summer 2002

Instructor:         J. Ramanujam (Ram)
Office:                 345 EE
Phone:                578-5628
E-mail:                jxr.ece.lsu.edu
Course time and place:   8:40-9:40 MTWTF in Room EE 145 (usually) or EE 117

Description: Neural networks and automata; network architectures; learning models; applications to signal processing, pattern recognition, data mining (vision, speech, and robotics); VLSI implementations.

Topics:

Introduction to neural networks, neurobiological analogies
McCulloch-Pitts neuron model
Feedforward networks: one-layer and multilayer
Backpropagation
Unsupervised learning: competitive and self-organizing feature maps
Recurrent networks: Hopfield model
Radial basis function networks
Support vector machines
Pattern recognition and data mining; optimization

Prerequisites: EE 3140 or MATH 4055, and CSC 1254 or equivalents

Grading:

25% Midterm(s)
30% Projects and Programs
20% Homework
25% Final exam

Reference texts:

On-line books:
M. Hagan, H. Demuth and M. Beale (1996), Neural Network Design, PWS Publishing, Boston, MA.
MATLAB (version 6.1) and MATLAB Neural Networks Toolbox (version 4.0):
C. Looney (1997), Pattern Recognition using Neural Networks, Oxford University Press, New York, NY.
J. Principe, N. Euliano, W. Lefebvre (2000), Neural and Adaptive Systems, John Wiley & Sons, New York, NY.
C. M. Bishop (1995), Neural Networks for Pattern Recognition, Oxford University Press, Oxford, UK.
J. Hertz, A. Krogh, R. Palmer (1991). Introduction to the Theory of Neural Computation, Addison-Wesley, Redwood City, CA.
L. Fausett (1994), Fundamentals of Neural Networks: Architectures, Algorithms, and Applications, Prentice-Hall, Englewood Cliffs, NJ.