Training a kind of hybrid universal learning networks with classification problems

Dazi Li; Kotaro Hirasawa; Jinglu Hu; Junichi Murata

Training a kind of hybrid universal learning networks with classification problems

Dazi Li, Kotaro Hirasawa, Jinglu Hu, Junichi Murata

Section of Measurement and Control Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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 language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks
Pages	703-708
Number of pages	6
Volume	1
Publication status	Published - 2002
Event	2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, United States Duration: May 12 2002 → May 17 2002

Other

Other	2002 International Joint Conference on Neural Networks (IJCNN '02)
Country/Territory	United States
City	Honolulu, HI
Period	5/12/02 → 5/17/02

All Science Journal Classification (ASJC) codes

Software
Artificial Intelligence

Cite this

@inproceedings{9311e2307bff4317bd16c6314f48fc67,

title = "Training a kind of hybrid universal learning networks with classification problems",

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.",

author = "Dazi Li and Kotaro Hirasawa and Jinglu Hu and Junichi Murata",

year = "2002",

language = "English",

volume = "1",

pages = "703--708",

booktitle = "Proceedings of the International Joint Conference on Neural Networks",

note = "2002 International Joint Conference on Neural Networks (IJCNN '02) ; Conference date: 12-05-2002 Through 17-05-2002",

}

TY - GEN

T1 - Training a kind of hybrid universal learning networks with classification problems

AU - Li, Dazi

AU - Hirasawa, Kotaro

AU - Hu, Jinglu

AU - Murata, Junichi

PY - 2002

Y1 - 2002

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0036077067&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036077067&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0036077067

VL - 1

SP - 703

EP - 708

BT - Proceedings of the International Joint Conference on Neural Networks

T2 - 2002 International Joint Conference on Neural Networks (IJCNN '02)

Y2 - 12 May 2002 through 17 May 2002

ER -

Training a kind of hybrid universal learning networks with classification problems

Abstract

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this