CAP 6615 — Neural Networks for Computing

TA: Raazia Mazhar
Office: CSE E309
Office hours: Tuesday, 5th and 6th period

Course Description

• Objectives: Understand the concepts and learn the techniques of neural network computing.
• Prerequisites: A familiarity with basic concepts in calculus, linear algebra, and probability theory. Calculus requirements include: differentiation, chain rule, integration. Linear algebra requirements include: matrix multiplication, inverse, pseudo-inverse.
• Main topics: Introduction to neural computational models including classification, association, optimization, and self-organization. Learning and discovery. Knowledge-based neural network design and algorithms.
• Applications include: pattern recognition, expert systems, control, signal analysis, and computer vision.



• Requirements: About six sets of homework (not to be handed in). Four to six projects in building neural networks for solving practical problems. The projects are graded and will be due periodically.
• Examinations: Two Exams one of which will be the Midterm. The first Midterm will be given approximately at the middle of the semester and the second will be in the last week of classes.
• Grading: Each exam counts 30% and the projects count 40% of the final grade.

Syllabus

• Basic neural computational models
• Feedforward networks
• Learning / backpropagation
• Association networks
• Classification
• Self-Organization
• Radial Basis Function networks
• Support Vector Machines
• Networks based on lattice computation
• Applications

Recommended Resources

Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory By Madan M. Gupta, Liang Jin, Noriyasu Homma Publisher: John Wiley & Sons, 2003 ISBN: 0471219487

Neural Networks: A Comprehensive Foundation By Simon S. Haykin Publisher: Prentice Hall, 2nd edition, 1998 ISBN: 0132733501

Pattern Classification By Richard O. Duda, Peter E. Hart, David G. Stork Publisher: Wiley-Interscience, 2nd edition, 2000 ISBN: 0471056693