CMU Artificial Intelligence Repository
Home INFO Search FAQs Repository Root

GANNET: Genetic Algorithm / Neural NETwork

This directory contains GANNET (Genetic Algorithm / Neural NETwork). GANNET allows one to evolve neural networks using genetic algorithms. GANNET evolves nets based upon three fitness functions: Input/Output Accuracy, Output 'Stability', and Network Size. The evolved neural network presently has a binary input and binary output format, with neurodes that have either 2 or 4 inputs and weights ranging from -3 to +4. GANNET only allows for 250 neurodes in a net. The distribution includes source code, a verifier program that verifies the best neural network generated, and some sample datasets.
Origin: []

Version: 0.91 (5-SEP-90, 8-SEP-92) Requires: ANSI C, UNIX Copying: Copyright (C) 1990 Jason J. Spofford GNU GPL v1 CD-ROM: Prime Time Freeware for AI, Issue 1-1 Author(s): Written by Captain Jason J. Spofford, USAF. Contact: Darrell Duane Dr. Kenneth Hintz George Mason University Dept. of Electrical & Computer Engineering Mail Stop 1G5 4400 University Drive Fairfax, VA 22033-4444 USA Tel: (703) 993-1592 Keywords: Authors!Spofford, C!Code, GANNET, GNU GPL, Genetic Algorithms, Neural Networks References: ?
Last Web update on Mon Feb 13 10:22:51 1995