New random search method for neural network learning - RasID

Jinglu Hu, Kotaro Hirasawa, Junichi Mutata, Masanao Ohbayashi, Yurio Eki

Research output: Contribution to conferencePaper

Abstract

This paper presents a novel random searching scheme called RasID for neural networks training. The idea is to introduce a sophisticated probability density function (PDF) for generating search vector. The PDF provides two parameters for realizing intensified search in the area where it is likely to find good solutions locally or diversified search in order to escape from a local minimum based on the success-failure of the past search. Gradient information is used to improve the search performance. The proposed scheme is applied to layered neural networks training and is benchmarked against other deterministic and non-deterministic methods.

Original languageEnglish
Pages2346-2351
Number of pages6
Publication statusPublished - 1998 Jan 1
Externally publishedYes
EventProceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3) - Anchorage, AK, USA
Duration: 1998 May 41998 May 9

Other

OtherProceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3)
CityAnchorage, AK, USA
Period98/5/498/5/9

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'New random search method for neural network learning - RasID'. Together they form a unique fingerprint.

  • Cite this

    Hu, J., Hirasawa, K., Mutata, J., Ohbayashi, M., & Eki, Y. (1998). New random search method for neural network learning - RasID. 2346-2351. Paper presented at Proceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3), Anchorage, AK, USA, .