CMU Artificial Intelligence Repository
Newton: Demonstrations of backpropagation neural networks.
areas/neural/systems/newton/
This directory contains a few demonstration programs to illustrate
backpropagation neural networks. These programs demonstrate two
features that one rarely finds in backpropagation neural nets:
(1) Newton's Method is used to update weights and threshold biases,
(2) Recurrence is allowed, with "persistent activations" (the
activation level of cells in the neural net is preserved
between steps).
Version: 12-NOV-90
Requires: Microsoft Quick Basic 4.5
Ports: IBM PCs
Copying: Use, copying, modification, and distribution permitted.
CD-ROM: Prime Time Freeware for AI, Issue 1-1
Author(s): Mark Hopkins
Milwaukee, Wisconsin
Keywords:
Authors!Hopkins, Backpropagation,
Machine Learning!Neural Networks, Neural Networks,
Newton's Method
References: ?
Last Web update on Mon Feb 13 10:25:30 1995
AI.Repository@cs.cmu.edu