Simplified intelligence single particle optimization based neural network for digit recognition

Jiarui Zhou, Zhen Ji, Linlin Shen

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

15 Citations (Scopus)

Abstract

To overcome the drawback of overly dependence on the input parameters in intelligence single particle optimization (ISPO), an improved algorithm, called simplified intelligence single particle optimization (SISPO), is proposed in this paper. While maintaining similar performance as ISPO, no special parameter settings are required by SISPO. The proposed SISPO was successfully applied to train neural network classifier for digit recognition. Experimental results demonstrated that, the proposed neural network training algorithm, Simplified Intelligence Single Particle Optimization Neural Network (SISPONN), achieved less training error and test error than traditional BP algorithms like gradient methods.

Original languageEnglish
Title of host publicationProceedings of the 2008 Chinese Conference on Pattern Recognition, CCPR 2008
Pages349-353
Number of pages5
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event2008 Chinese Conference on Pattern Recognition, CCPR 2008 - Beijing, China
Duration: 22 Oct 200824 Oct 2008

Publication series

NameProceedings of the 2008 Chinese Conference on Pattern Recognition, CCPR 2008

Conference

Conference2008 Chinese Conference on Pattern Recognition, CCPR 2008
Country/TerritoryChina
CityBeijing
Period22/10/0824/10/08

Keywords

  • Digital recognition
  • Intelligence single particle optimization
  • ISPO
  • Neural network

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Simplified intelligence single particle optimization based neural network for digit recognition'. Together they form a unique fingerprint.

Cite this