CMU Artificial Intelligence Repository
TCS: Tasmanian Connectionist Simulator
areas/neural/systems/tcs/
TCS (Tasmanian Connectionist Simulator) is a neural network
simulation package written in Borland C++ for MS Windows.
Examples include an interactive activation network for 4-letter words,
the Rescorla-Wagner model of classical conditioning, Schnys's
Clustering Network (uses a non-supervised Kohonen-style learning
rule), and an XOR network using backpropagation.
Origin:
ftp.psychol.utas.edu.au:/pub/tcs [131.217.35.98]
Version: 4-AUG-93
Requires: C++, Microsoft Windows
CD-ROM: Prime Time Freeware for AI, Issue 1-1
Author(s): Dr Zoltan Schreter .
Department of Psychology
University of Tasmania
GPO Box 252C
Hobart, Tasmania 7001
AUSTRALIA
Tel: +61 02 20 2887
Fax: +61 02 20 2883
Keywords:
Authors!Schreter, Backpropagation, C++!Code, Conditioning,
Connectionist Systems, Extinction, Kohonen,
Machine Learning!Neural Networks, Neural Networks!Simulators,
TCS, XOR
Contains:
exe*.zip Compiled executable versions of the examples
tcs.zip TCS, including C++ source, manuals, and examples
References:
McClelland, J.L. and Rumelhart, D., "An interactive activation model
of context effects in letter perception", Part1, Psychological Review,
88:375-407, 1981.
Rescorla, R.A. and Wagner, A.R., "A theory of Psvlovian conditioning:
variations in the effectiveness of reinforcement and
non-reinforcement", in Black, A.H. and Prokasy W.F. (Eds.), Classical
conditioning (Vol 2). New York: Appleton-Century-Crofts.
Schnys, P.G., "A modular neural network model of concept
acquisition", Cognitive Science 15:461-508, 1991.
Last Web update on Mon Feb 13 10:25:38 1995
AI.Repository@cs.cmu.edu