Interactive simulation of backpropagation and creeping-random-search learning in neural networks

A new environment for interactive neural-network experiments on personal computers, DESIRE/NEUNET combines a readable matrix language with very fast "direct execution". Experimenters enter and screen-edit simulation programs and run immediately, without the usual annoying delays for compil...

Full description

Saved in:
Bibliographic Details
Published in:Simulation (San Diego, Calif.) Calif.), 1990-10, Vol.55 (4), p.214-219
Main Author: Korn, Granino A.
Format: Article
Language:English
Subjects:
Associative memory
Back propagation
Computer simulation
Differential equations
Interactive
Learning
Neural networks
Searching
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A new environment for interactive neural-network experiments on personal computers, DESIRE/NEUNET combines a readable matrix language with very fast "direct execution". Experimenters enter and screen-edit simulation programs and run immediately, without the usual annoying delays for compilation and linking. Simula tions still run much faster than Microsoft FORTRAN. Users can compose their own help screens and interactive menus. DESIRE/ NEUNET permits conventional dynamic-system simulation (up to 1000 differential equations) as well as, or in conjunction with, neural-net simulation and has been used to simulate Hopfield and bidirectional associative memories, transver sal predictors, and various competitive- learning schemes. This report exhibits the classical XOR training experiment with backpropagation and creeping-random- search learning.
ISSN:0037-5497
1741-3133
DOI:10.1177/003754979005500403