NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Pseudogradient Training For A Class Of Neural NetworksDevelopmental second-order recurrent neural networks of special type modified to enhance stability in face of inputs beyond range of inputs on which trained. Second-order recurrent neural networks contain product feedback units and can be trained, by use of example inputs and outputs, to act as finite-state automatons. Particular second-order recurrent neural networks in question learn grammars in sense they are trained to generate binary responses to input training sequences of ones and zeros, each sequence being marked "legal" or "illegal" according to grammar to be learned.
Document ID
19950065617
Acquisition Source
Legacy CDMS
Document Type
Other - NASA Tech Brief
Authors
Zeng, Zheng
(Caltech)
Goodman, Rodney M.
(Caltech)
Smyth, Padhraic J.
(Caltech)
Date Acquired
August 17, 2013
Publication Date
September 1, 1995
Publication Information
Publication: NASA Tech Briefs
Volume: 19
Issue: 9
ISSN: 0145-319X
Subject Category
Mathematics And Information Sciences
Report/Patent Number
NPO-18956
Accession Number
95B10458
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.

Available Downloads

There are no available downloads for this record.
No Preview Available