Course Description
Programs that solve complex problems in a particular domain, typically independent of knowledge used to direct the search for an optimal solution. Approaches include simulated annealing, genetic algorithms, neural networks.
Athena Title
COMPUT INTELLIGENCE
Prerequisite
CSCI(PHIL) 4550/6550 or permission of department
Semester Course Offered
Not offered on a regular basis.
Grading System
A - F (Traditional)
Course Objectives
Students will gain a working knowledge of the three primary computational intelligence approaches: simulated annealing, genetic algorithms, and artificial neural networks. The main focus will be on the details of the techniques, understanding why the techniques produce accurate results, identifying the types of problems each technique is suited for, and determining those problem areas for which a technique would be inappropriate. Students will receive "hands-on" experience with experimental computer science via class and lab exercises.
Topical Outline
I. Introduction to computational intelligence, II. Overview of simulated annealing (SA), III. SA representation and temperature control, IV. SA problems, V. Overview of genetic algorithms (GA), VI. GA representation and fitness, VII. GA schema theorem and classifiers, VIII. GA problems, IX. Overview of neural networks (NN), X. NN nodes and layers, XI. NN weights and back-propagation, XII. NN problems, XIII. Other approaches to computational intelligence.