Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Artificial neural networks: a science in trouble

Artificial neural networks: a science in trouble This article points out some very serious misconceptions about the brain in connectionism and artificial neural networks. Some of the connectionist ideas have been shown to have logical flaws, while others are inconsistent with some commonly observed human learning processes and behavior. For example, the connectionist ideas have absolutely no provision for learning from stored information, something that humans do all the time. The article also argues that there is definitely a need for some new ideas about the internal mechanisms of the brain. It points out that a very convincing argument can be made for a "control theoretic" approach to understanding the brain. A "control theoretic" approach is actually used in all connectionist and neural network algorithms and it can also be justified from recent neurobiological evidence. A control theoretic approach proposes that there are subsystems within the brain that control other subsystems. Hence a similar approach can be taken in constructing learning algorithms and other intelligent systems. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM SIGKDD Explorations Newsletter Association for Computing Machinery

Artificial neural networks: a science in trouble

Roy, Asim
ACM SIGKDD Explorations Newsletter , Volume 1 (2) – Jan 1, 2000
Download PDF
6 pages

Loading next page...
 
/lp/association-for-computing-machinery/artificial-neural-networks-a-science-in-trouble-QEpusVcBQ5
Publisher
Association for Computing Machinery
Copyright
Copyright © 2000 by ACM Inc.
ISSN
1931-0145
DOI
10.1145/846183.846192
Publisher site
See Article on Publisher Site

Abstract

This article points out some very serious misconceptions about the brain in connectionism and artificial neural networks. Some of the connectionist ideas have been shown to have logical flaws, while others are inconsistent with some commonly observed human learning processes and behavior. For example, the connectionist ideas have absolutely no provision for learning from stored information, something that humans do all the time. The article also argues that there is definitely a need for some new ideas about the internal mechanisms of the brain. It points out that a very convincing argument can be made for a "control theoretic" approach to understanding the brain. A "control theoretic" approach is actually used in all connectionist and neural network algorithms and it can also be justified from recent neurobiological evidence. A control theoretic approach proposes that there are subsystems within the brain that control other subsystems. Hence a similar approach can be taken in constructing learning algorithms and other intelligent systems.

Journal

ACM SIGKDD Explorations Newsletter – Association for Computing Machinery

Published: Jan 1, 2000

There are no references for this article.