본문 바로가기
  • Home

A Spatiotemporal Parallel Processing Model for the MLP Neural Network

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2005, 10(5), pp.95-102
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science

Sungoan Kim 1

1수원과학대학

Candidate

ABSTRACT

A parallel processing model by considering a spatiotemporal parallelism is presented for the training procedure of the MLP neural network. We tried to design the flexible parallel processing model by simultaneously applying both of the training-set decomposition for a temporal parallelism and the network decomposition for a spatial parallelism. The analytical performance evaluation model shows that when the problem size is extremely large, the speedup of each implementation depends, in the extreme, on whether the problem size is pattern-size intensive or pattern-quantity intensive.

Citation status

* References for papers published after 2023 are currently being built.