A constraints-embeded OBS process and conjugate gradient optimizing algorithm

Cui Juan Wu*, Dong Li, Tian Song

*Corresponding author for this work

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

Abstract

The optimal brain surgeon(OBS) process is a high computing complexity post-training network pruning algorithm. A OBS conjugate gradient structure optimizing algorithm(c-OBS-CG) constraints embeded was designed which regarded the structure evaluating relationship as constraints and introduced it into neural network trainging target function, and aided by the mix process of Newton gradient and conjugate gradient. The simulation experiment verify its validity. It implements the parallel pruning of network training and OBS process, keeps both the accuracy of OBS procedure and highly-efficient regularization, raises the generalization performance of neural network.

Original languageEnglish
Title of host publicationProceedings - International Conference on Electrical and Control Engineering, ICECE 2010
Pages23-26
Number of pages4
DOIs
Publication statusPublished - 2010
EventInternational Conference on Electrical and Control Engineering, ICECE 2010 - Wuhan, China
Duration: 26 Jun 201028 Jun 2010

Publication series

NameProceedings - International Conference on Electrical and Control Engineering, ICECE 2010

Conference

ConferenceInternational Conference on Electrical and Control Engineering, ICECE 2010
Country/TerritoryChina
CityWuhan
Period26/06/1028/06/10

Keywords

  • Conjugate gradient
  • Constraints
  • Network pruning
  • Neural network
  • Optimal brain surgeon process

Fingerprint

Dive into the research topics of 'A constraints-embeded OBS process and conjugate gradient optimizing algorithm'. Together they form a unique fingerprint.

Cite this