CMU Artificial Intelligence Repository
NN-Simulator: Flexible and User-Friendly Neural Network
Simulator
areas/neural/systems/simul/
The simulate program is a user-friendly and flexible neural network
simulator. It is designed to handle the simulation of associative
learning style networks, such as the LMS (aka Rescorla-Wagner)
learning procedure and Backpropagation. Multiple interacting networks
can be simulated in parallel, with their behavior and interactions
specified by a simple command language.
Some of the more useful features of the simulator include:
- Simulation weights can be saved, and later used to initialize the
weights of a new simulation.
- Multilayer networks with arbitrary interconnectivity can be
created.
- Quickprop, a faster version of backpropagation is supported.
- Network behavior on each cycle in the simulation can be
specified.
- The output of the simulation on each cycle can be specified.
The example network files include:
- ENCODER. Simulation files for a 10-5-10 encoder (described in
(Rumelhart & McClelland, 1986 v.1). Demonstrates a simple
backpropagation network.
- HINTON. Simulation files for Hinton's "family tree problem"
(Hinton, 1986). This demonstrates a more sophisticated
example of backpropagation: the network is six layers instead of 3.
Includes both backprop and quickprop versions of the network.
- SHANKS. Simulation files for some simple linear associative
networks (discussed in Shanks, 1991).
Origin:
ftp.cognet.ucla.edu:/pub/THNET/NN-SIMULATOR/ [128.97.8.19]
Version: 26-JUN-93
Requires: C
CD-ROM: Prime Time Freeware for AI, Issue 1-1
Author(s): Eric Melz
UCLA Department of Psychology
Franz Hall, UCLA
Los Angeles, CA, 90024 USA
Tel: (310) 825-8712
Keywords:
Associative Learning Networks, Authors!Melz, Backpropagation,
C!Code, LMS Learning Procedure, Linear Associative Networks,
Machine Learning!Neural Networks, Neural Networks!Simulators,
Quickprop, Rescorla-Wagner Learning Procedure
References: ?
Last Web update on Mon Feb 13 10:25:35 1995
AI.Repository@cs.cmu.edu