Dynamical configuration of neural network architectures

Jun Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

A dynamical configurable architecture for feedforward artificial neural networks (ANNs) is proposed. A dynamical configuration rule based on a general topological structure for feedforward neural networks and an adaptive learning algorithm are presented. The two combined provide an automated paradigm for synthesis of feedforward ANNs that has the potential to generate the optimal ANN representations for arbitrary training samples. Since the size of the architecture is determined by the dynamical configuration rule autonomously, this paradigm is advantageous in terms of convenience of architectural realization and reduction of computational time.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
PublisherPubl by IEEE
Pages376-378
Number of pages3
ISBN (Print)0879425970
Publication statusPublished - Nov 1990
Externally publishedYes
Event1990 IEEE International Conference on Systems, Man, and Cybernetics - Los Angeles, CA, USA
Duration: 4 Nov 19907 Nov 1990

Publication series

NameProceedings of the IEEE International Conference on Systems, Man and Cybernetics
ISSN (Print)0884-3627

Conference

Conference1990 IEEE International Conference on Systems, Man, and Cybernetics
CityLos Angeles, CA, USA
Period4/11/907/11/90

Fingerprint

Dive into the research topics of 'Dynamical configuration of neural network architectures'. Together they form a unique fingerprint.

Cite this