GANNET:

GANNET (Genetic Algorithm / Neural NETwork) is a software package written by Jason Spofford in 1990 which allows one to evolve binary valued neural networks. It offers a variety of configuration options related to rates of the GENETIC OPERATORs. 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 allows for up to 250 neurons in a net. Research using GANNET is continuing.

GANNET 2.0 is available at http://fame.gmu.edu/~dduane/thesis . As well as the software, the masters thesis that utilized this program as well as a paper is available in this directory. See also ftp://fame.gmu.edu/gannet/source/

The major enhancement of version 2.0 is the ability to recognize variable length binary strings, such as those that would be generated by a finite automaton. Included is code for calculating the Effective Measure Complexity (EMC) of finite automata as well as code for generating test data.

A mailing list has been established for discussing uses and problems with the GANNET software. To subscribe, send a message to: <listproc@gmu.edu> On the first line of the message (not the subject) type: SUB GANNET Your-First-Name Your-Last-Name

Contact: Darrell Duane or Dr. Kenneth Hintz, George Mason University, Dept. of Electrical & Computer Engineering, Mail Stop 1G5, 4400 University Drive, Fairfax, VA 22033-4444 USA. Net: <dduane@fame.gmu.edu> or <khintz@fame.gmu.edu>