Mathematical foundations of neurocomputing

Author

Amari, Shun-Ichi

Author_Institution

Fac. of Eng., Tokyo Univ., Japan

Volume

78

Issue

9

fYear

1990

fDate

9/1/1990 12:00:00 AM

Firstpage

1443

Lastpage

1463

Abstract

An attempt is made to establish a mathematical theory that shows the intrinsic mechanisms, capabilities, and limitations of information processing by various architectures of neural networks. A method of statistically analyzing one-layer neural networks is given, covering the stability of associative mapping and mapping by totally random networks. A fundamental problem of statistical neurodynamics is considered in a way that is different from the spin-glass approach. A dynamic analysis of associative memory models and a general theory of neural learning, in which the learning potential function plays a role, are given. An advanced theory of learning and self-organization is proposed, covering backpropagation and its generalizations as well as the formation of topological maps and neural representations of information

Keywords

content-addressable storage; learning systems; neural nets; statistical analysis; topology; associative mapping; associative memory models; backpropagation; information processing; neural learning; neural networks; neurocomputing; statistical neurodynamics; topological maps; Associative memory; Biological neural networks; Brain modeling; Evolution (biology); Humans; Information analysis; Information processing; Information representation; Mathematical model; Neurodynamics;

fLanguage

English

Journal_Title

Proceedings of the IEEE

Publisher

ieee

ISSN

0018-9219

Type

jour

DOI

10.1109/5.58324

Filename

58324