CMU Artificial Intelligence Repository
RNS: Recurrent Network Simulator
areas/neural/systems/rns/
RNS (Recurrent Network Simulator) is a simulator for recurrent neural
networks. Regular neural networks are also supported. The program uses
a derivative of the back-propagation algorithm, but also includes
other (not that well tested) algorithms.
Features include
- freely choosable connections, no restrictions besides memory
or CPU constraints
- delayed links for recurrent networks
- fixed values or thresholds can be specified for weights
- (recurrent) back-propagation, Hebb, differential Hebb, simulated
annealing and more
- patterns can be specified with bits, floats, characters, numbers, and
random bit patterns with Hamming distances can be chosen for you
- user definable error functions
- output results can be used without modification as input
Origin:
dnpap.et.tudelft.nl:/pub/Private/Richard/Rns/
as the files rns-1.6b.tar.gz and rns-wpdoc.zip
Version: 1.6b (5-MAR-94)
Requires: C
Ports: IBM PCs and Sun Workstations (SunOS 4.x)
Copying: Public Domain
CD-ROM: Prime Time Freeware for AI, Issue 1-1
Author(s): Richard Kooijman
Delft University of Technology
Department of Electrical Engineering
Section Computer Architecture and Digital Technique
Mekelweg 4
2628 CD Delft
The Netherlands
Tel: +31-15-786209
Fax: +31-15-784898
Keywords:
Authors!Kooijman, Backpropagation, C!Code,
Connectionist Systems, Hebbian Learning,
Machine Learning!Neural Networks, Neural Networks!Simulators,
Public Domain, RNS, Recurrent Neural Networks
References: ?
Last Web update on Mon Feb 13 10:25:34 1995
AI.Repository@cs.cmu.edu