CMU Artificial Intelligence Repository
NevProp: General purpose backpropagation in C.
areas/neural/systems/nevprop/
NevProp is a C implementation of general purpose backpropagation
software, based on Quickprop 1.0 by Scott Fahlman, as translated from
Common Lisp into C by Terry Regier. The quickprop algorithm itself
has not changed substantially, but it now includes options to force
gradient descent (per-epoch or per-pattern), generalization & stopped
training, c index, and interface enhancements.
Questions and comments regarding the Quickprop algorithm itself should
be directed to Scott Fahlman at sef+@cs.cmu.edu. Issues pertaining
to NevProp code or functionality itself should be directed to the authors.
Origin:
unssun.scs.unr.edu:/pub/goodman/nevpropdir/ [134.197.10.128]
as the file npxxx.shar (replace xxx with the version number)
or from the CMU Simulator Collection.
Version: 1.16 (13-JUL-93)
Requires: C
Ports: It runs on Unix, Macintosh, and DOS.
CD-ROM: Prime Time Freeware for AI, Issue 1-1
Author(s): Phil Goodman
David Rosen, Allen Plummer
University of Nevada
Center for Biomedical Modeling Research
Washoe Medical Center, H-166,
77 Pringle Way
Reno, NV 89520
Tel: 702-328-4867
Fax: 702-328-4111
Keywords:
Authors!Fahlman, Authors!Goodman, Authors!Plummer,
Authors!Rosen, Backpropagation, C!Code, Gradient Descent,
Machine Learning!Neural Networks, Neural Networks, NevProp,
Quickprop
References:
The algorithm and some test results are described in Fahlman's paper
"Faster-Learning Variations on Back-Propagation: An Empirical Study"
in Proceedings of 1988 Connectionist Models Summer School, published
by Morgan Kaufmann.
Last Web update on Mon Feb 13 10:25:29 1995
AI.Repository@cs.cmu.edu