logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

pRAM layout optimisation

delete1997-12-01
delete3
PRE
AI
B
Bruno Apolloni *
D
Diego de Falco
J
John G. Taylor
DOI：10.1016/S0893-6080(97)00030-0delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
We propose a procedure for designing the layout of a fixed fan-in neural network based on the pRAM model. Using minimisation of the relative entropy between environment and output probability distribution laws as a target, and Amari's learning rule as a strategy, we show that consideration of the conditional entropy of the output of one node, given the candidate nodes that provide its inputs, leads to a locally optimum choice of the the connections. The procedure is computationally feasible when certain preference criteria are used to control the mutual relevance of the pRAM nodes. We give some simple numerical examples of this procedure. (C) 1997 Elsevier Science Ltd. All rights reserved.
Keywords:
neural networks
layout optimisation
network architecture
probabilistic random access memory
entropy
relative entropy
information geometry
multivariate Bernoulli distribution
on-line statistics
AI Summary

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.

Journal

Neural Networks cover
Neural Networks
IF:
6.3
Papers:
7.8K
Citations:
3.0W

Organization

No organization information available