Object oriented learning network and its applications

Takayuki Furuzuki, Kotaro Hirasawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper introduces an scheme to construct object oriented learning networks (OOLN). The idea is to construct a learning network with two levels. The high-level network is built based on application specific prior knowledge such that it has a structure favorable to the applications. And the low-level one consists of a class of conventional neural networks. The OOLN is expected to have both application flexibility and representation flexibility.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Place of PublicationUnited States
PublisherIEEE
Pages1298-1301
Number of pages4
Volume2
Publication statusPublished - 1999
Externally publishedYes
EventInternational Joint Conference on Neural Networks (IJCNN'99) - Washington, DC, USA
Duration: 1999 Jul 101999 Jul 16

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'99)
CityWashington, DC, USA
Period99/7/1099/7/16

Fingerprint

Neural networks

ASJC Scopus subject areas

  • Software

Cite this

Furuzuki, T., & Hirasawa, K. (1999). Object oriented learning network and its applications. In Proceedings of the International Joint Conference on Neural Networks (Vol. 2, pp. 1298-1301). United States: IEEE.

Object oriented learning network and its applications. / Furuzuki, Takayuki; Hirasawa, Kotaro.

Proceedings of the International Joint Conference on Neural Networks. Vol. 2 United States : IEEE, 1999. p. 1298-1301.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Furuzuki, T & Hirasawa, K 1999, Object oriented learning network and its applications. in Proceedings of the International Joint Conference on Neural Networks. vol. 2, IEEE, United States, pp. 1298-1301, International Joint Conference on Neural Networks (IJCNN'99), Washington, DC, USA, 99/7/10.
Furuzuki T, Hirasawa K. Object oriented learning network and its applications. In Proceedings of the International Joint Conference on Neural Networks. Vol. 2. United States: IEEE. 1999. p. 1298-1301
Furuzuki, Takayuki ; Hirasawa, Kotaro. / Object oriented learning network and its applications. Proceedings of the International Joint Conference on Neural Networks. Vol. 2 United States : IEEE, 1999. pp. 1298-1301
@inproceedings{0e83b8bfe6ea4b558b1087b5a83eab9a,
title = "Object oriented learning network and its applications",
abstract = "This paper introduces an scheme to construct object oriented learning networks (OOLN). The idea is to construct a learning network with two levels. The high-level network is built based on application specific prior knowledge such that it has a structure favorable to the applications. And the low-level one consists of a class of conventional neural networks. The OOLN is expected to have both application flexibility and representation flexibility.",
author = "Takayuki Furuzuki and Kotaro Hirasawa",
year = "1999",
language = "English",
volume = "2",
pages = "1298--1301",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "IEEE",

}

TY - GEN

T1 - Object oriented learning network and its applications

AU - Furuzuki, Takayuki

AU - Hirasawa, Kotaro

PY - 1999

Y1 - 1999

N2 - This paper introduces an scheme to construct object oriented learning networks (OOLN). The idea is to construct a learning network with two levels. The high-level network is built based on application specific prior knowledge such that it has a structure favorable to the applications. And the low-level one consists of a class of conventional neural networks. The OOLN is expected to have both application flexibility and representation flexibility.

AB - This paper introduces an scheme to construct object oriented learning networks (OOLN). The idea is to construct a learning network with two levels. The high-level network is built based on application specific prior knowledge such that it has a structure favorable to the applications. And the low-level one consists of a class of conventional neural networks. The OOLN is expected to have both application flexibility and representation flexibility.

UR - http://www.scopus.com/inward/record.url?scp=0033334208&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033334208&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 1298

EP - 1301

BT - Proceedings of the International Joint Conference on Neural Networks

PB - IEEE

CY - United States

ER -