Training a kind of hybrid universal learning networks with classification problems

Dazi Li, Kotaro Hirasawa, Jinglu Hu, Junichi Murata

Research output: Contribution to conferencePaper

Abstract

In the search for even better parsimonious neural network modeling, this paper describes a novel approach which attempts to exploit redundancy found in the conventional sigmoidal networks. A hybrid universal learning network constructed by the combination of proposed multiplication units with summation units is trained for several classification problems. It is clarified that the multiplication units in different layers in the network improve the performance of the network.

Original languageEnglish
Pages703-708
Number of pages6
Publication statusPublished - 2002 Jan 1
Externally publishedYes
Event2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, United States
Duration: 2002 May 122002 May 17

Conference

Conference2002 International Joint Conference on Neural Networks (IJCNN '02)
CountryUnited States
CityHonolulu, HI
Period02/5/1202/5/17

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Training a kind of hybrid universal learning networks with classification problems'. Together they form a unique fingerprint.

  • Cite this

    Li, D., Hirasawa, K., Hu, J., & Murata, J. (2002). Training a kind of hybrid universal learning networks with classification problems. 703-708. Paper presented at 2002 International Joint Conference on Neural Networks (IJCNN '02), Honolulu, HI, United States.