Open Access
Translator Disclaimer
May, 1991 Neural Nets and Implicit Inference
P. Whittle
Ann. Appl. Probab. 1(2): 173-188 (May, 1991). DOI: 10.1214/aoap/1177005932

Abstract

The contention that artificial neural nets operate by a process of distributed hypothesis testing is supported by analysis of the antiphon, a model which is close to standard associative-memory models but is intended primarily to represent memory storage under stochastic disturbance of the system. The memory capacity of the antiphon under "neuronal" inference rules has been evaluated elsewhere; here it is evaluated under the supposition of efficient inference procedures.

Citation

Download Citation

P. Whittle. "Neural Nets and Implicit Inference." Ann. Appl. Probab. 1 (2) 173 - 188, May, 1991. https://doi.org/10.1214/aoap/1177005932

Information

Published: May, 1991
First available in Project Euclid: 19 April 2007

zbMATH: 0803.62003
MathSciNet: MR1102315
Digital Object Identifier: 10.1214/aoap/1177005932

Subjects:
Primary: 62H15
Secondary: 93A15 , 94A24

Keywords: antiphon , association , channel coding , Hopfield net , memory , Neural nets

Rights: Copyright © 1991 Institute of Mathematical Statistics

JOURNAL ARTICLE
16 PAGES


SHARE
Vol.1 • No. 2 • May, 1991
Back to Top