Parallel architectures for artificial neural nets.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

28 Scopus citations

Abstract

The key aspects of the modeling, algorithm, and architecture for artificial neural nets (ANNs) is reviewed. A programmable systolic array meant for a variety of connectivity patterns for ANNs is proposed. Considered in the design are both the search and learning phases of a class of ANNs. A system-theoretic approach is adopted to elucidate modeling issues for ANNs. On this basis the issues of expressibility and discrimination, fault tolerance and generalization, size of hidden units/layers, interconnectivity patterns, and circuit model for analog ANN implementations are addressed.

Original languageEnglish (US)
Title of host publicationProc Int Conf on Systolic Arrays
PublisherPubl by IEEE
Pages163-174
Number of pages12
ISBN (Print)0818688602
StatePublished - Dec 1 1988

Publication series

NameProc Int Conf on Systolic Arrays

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Fingerprint Dive into the research topics of 'Parallel architectures for artificial neural nets.'. Together they form a unique fingerprint.

  • Cite this

    Kung, S-Y. (1988). Parallel architectures for artificial neural nets. In Proc Int Conf on Systolic Arrays (pp. 163-174). (Proc Int Conf on Systolic Arrays). Publ by IEEE.