Skip to main navigation Skip to search Skip to main content

Research and design of distributed neural networks with chip training algorithm

  • School of Computer Science and Technology, Harbin Institute of Technology

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

Abstract

To solve the bottleneck of memory in current prediction of protein secondary structure program, a chip training algorithm for a Distributed Neural Networks based on multi-agents is proposed in this paper. This algorithm evolves the global optimum by competition from a group of neural network agents by processing different groups of sample chips. The experimental results demonstrate that this method can effectively improve the convergent speed, has good expansibility, and can be applied to the prediction of protein secondary structure of middle and large size of amino-acid sequence.

Original languageEnglish
Title of host publicationAdvances in Natural Computation
Subtitle of host publication1st International Conference, ICNC 2005 - Proceedings
PublisherSpringer Verlag
Pages213-216
Number of pages4
EditionPART I
ISBN (Print)9783540283232
DOIs
StatePublished - 2005
Externally publishedYes
Event1st International Conference on Natural Computation, ICNC 2005 - Changsha, China
Duration: 27 Aug 200529 Aug 2005

Publication series

NameLecture Notes in Computer Science
NumberPART I
Volume3610
ISSN (Print)0302-9743

Conference

Conference1st International Conference on Natural Computation, ICNC 2005
Country/TerritoryChina
CityChangsha
Period27/08/0529/08/05

Fingerprint

Dive into the research topics of 'Research and design of distributed neural networks with chip training algorithm'. Together they form a unique fingerprint.

Cite this