Universal learning networks with multiplication neurons and its representation ability

D. Li, K. Hirasawa, J. Hu, J. Murata

Research output: Contribution to conferencePaper

5 Citations (Scopus)

Abstract

Universal Learning Networks(ULNs) which are super set of supervised learning networks have been already proposed. They consist of a number of inter-connected nodes where the nodes may have any continuously differentiable nonlinear functions in them. Most of the functions used are sigmoidal functions. Disadvantages of exiting ULNs mainly lie in that long training time, a large number of nodes in hidden layers, and so on. In this paper, special ULNs with multiplication neurons(M neuron) are proposed, which have M neurons in the hidden layer and normal neurons with sigmoidal functions in the output layer. The computational power of networks models with multiplication neurons is compared with that of ULNs with existing neurons. In particular it is proved that ULNs with multiplication neurons are, with regard to the number of neurons that are needed, computationally more powerful than ULNs with normal sigmodial functions.

Original languageEnglish
Pages150-155
Number of pages6
Publication statusPublished - 2001 Jan 1
EventInternational Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, United States
Duration: 2001 Jul 152001 Jul 19

Conference

ConferenceInternational Joint Conference on Neural Networks (IJCNN'01)
CountryUnited States
CityWashington, DC
Period01/7/1501/7/19

    Fingerprint

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Li, D., Hirasawa, K., Hu, J., & Murata, J. (2001). Universal learning networks with multiplication neurons and its representation ability. 150-155. Paper presented at International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, United States.