Universal learning network and computation of its higher order derivatives

Kotaro Hirasawa, Masanao Ohbayashi, Junichi Murata

Research output: Contribution to conferencePaper

29 Citations (Scopus)

Abstract

In this paper, Universal Learning Network (U.L.N.) is presented, which models and controls large scale complicated systems such as industrial plants, economic, social and life phenomena, and also a computing method of higher order derivatives of U.L.N. is derived in order to obtain learning ability. The basic idea of U.L.N. is that large scale complicated systems can be modeled by the network which consists of nonlinearly operated nodes and branches which may have arbitrary time delays including zero or minus ones. It has not been presented that the network such as U.L.N. is able to model and control naturally the large scale complicated systems which can be seen commonly in the social and physical worlds. It is shown that first order derivatives of U.L.N. with sigmoid functions and one sampling time delays correspond to the back propagation learning algorithm of the recurrent neural network.

Original languageEnglish
Pages1273-1277
Number of pages5
Publication statusPublished - Dec 1 1995
EventProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) - Perth, Aust
Duration: Nov 27 1995Dec 1 1995

Other

OtherProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)
CityPerth, Aust
Period11/27/9512/1/95

All Science Journal Classification (ASJC) codes

  • Software

Fingerprint Dive into the research topics of 'Universal learning network and computation of its higher order derivatives'. Together they form a unique fingerprint.

  • Cite this

    Hirasawa, K., Ohbayashi, M., & Murata, J. (1995). Universal learning network and computation of its higher order derivatives. 1273-1277. Paper presented at Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, .