A T-Model neural network with learning ability

Okihiko Ishizuka; Zheng Tang; Tetsuya Inoue; Hiroki Matsumoto; Shogo Ohba

doi:10.1109/ijcnn.1991.170729

A T-Model neural network with learning ability

Okihiko Ishizuka^*, Zheng Tang, Tetsuya Inoue, Hiroki Matsumoto, Shogo Ohba

^*Corresponding author for this work

Intellectual Information Engineering

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

4 Scopus citations

Abstract

The authors introduce a novel neural network called the T-Model with learning capability. They utilized the least mean square algorithm to train the T-Model and exploit the learning capability of the introduced network. The architecture and the algorithm of the T-Model network are described. Some typical examples to illustrate the effectiveness of the algorithm are included and compared with the Hopfield model and a multilayer model. The simulations and experiments showed that the algorithm is quite effective in training the T-Model network for many problems.

Original language	English
Title of host publication	91 IEEE Int Jt Conf Neural Networks IJCNN 91
Publisher	Publ by IEEE
Pages	2288-2293
Number of pages	6
ISBN (Print)	0780302273, 9780780302273
DOIs	https://doi.org/10.1109/ijcnn.1991.170729
State	Published - 1991
Event	1991 IEEE International Joint Conference on Neural Networks - IJCNN '91 - Singapore, Singapore Duration: 1991/11/18 → 1991/11/21

Publication series

Name	91 IEEE Int Jt Conf Neural Networks IJCNN 91

Conference

Conference	1991 IEEE International Joint Conference on Neural Networks - IJCNN '91
City	Singapore, Singapore
Period	1991/11/18 → 1991/11/21

ASJC Scopus subject areas

General Engineering

Access to Document

10.1109/ijcnn.1991.170729

Cite this

@inproceedings{011ebc2a00634f0b89d7b9f9ffd9b395,

title = "A T-Model neural network with learning ability",

abstract = "The authors introduce a novel neural network called the T-Model with learning capability. They utilized the least mean square algorithm to train the T-Model and exploit the learning capability of the introduced network. The architecture and the algorithm of the T-Model network are described. Some typical examples to illustrate the effectiveness of the algorithm are included and compared with the Hopfield model and a multilayer model. The simulations and experiments showed that the algorithm is quite effective in training the T-Model network for many problems.",

author = "Okihiko Ishizuka and Zheng Tang and Tetsuya Inoue and Hiroki Matsumoto and Shogo Ohba",

year = "1991",

doi = "10.1109/ijcnn.1991.170729",

language = "英語",

isbn = "0780302273",

series = "91 IEEE Int Jt Conf Neural Networks IJCNN 91",

publisher = "Publ by IEEE",

pages = "2288--2293",

booktitle = "91 IEEE Int Jt Conf Neural Networks IJCNN 91",

note = "1991 IEEE International Joint Conference on Neural Networks - IJCNN '91 ; Conference date: 18-11-1991 Through 21-11-1991",

}

Ishizuka, O, Tang, Z, Inoue, T, Matsumoto, H & Ohba, S 1991, A T-Model neural network with learning ability. in 91 IEEE Int Jt Conf Neural Networks IJCNN 91. 91 IEEE Int Jt Conf Neural Networks IJCNN 91, Publ by IEEE, pp. 2288-2293, 1991 IEEE International Joint Conference on Neural Networks - IJCNN '91, Singapore, Singapore, 1991/11/18. https://doi.org/10.1109/ijcnn.1991.170729

TY - GEN

T1 - A T-Model neural network with learning ability

AU - Ishizuka, Okihiko

AU - Tang, Zheng

AU - Inoue, Tetsuya

AU - Matsumoto, Hiroki

AU - Ohba, Shogo

PY - 1991

Y1 - 1991

N2 - The authors introduce a novel neural network called the T-Model with learning capability. They utilized the least mean square algorithm to train the T-Model and exploit the learning capability of the introduced network. The architecture and the algorithm of the T-Model network are described. Some typical examples to illustrate the effectiveness of the algorithm are included and compared with the Hopfield model and a multilayer model. The simulations and experiments showed that the algorithm is quite effective in training the T-Model network for many problems.

AB - The authors introduce a novel neural network called the T-Model with learning capability. They utilized the least mean square algorithm to train the T-Model and exploit the learning capability of the introduced network. The architecture and the algorithm of the T-Model network are described. Some typical examples to illustrate the effectiveness of the algorithm are included and compared with the Hopfield model and a multilayer model. The simulations and experiments showed that the algorithm is quite effective in training the T-Model network for many problems.

UR - http://www.scopus.com/inward/record.url?scp=0026299685&partnerID=8YFLogxK

U2 - 10.1109/ijcnn.1991.170729

DO - 10.1109/ijcnn.1991.170729

M3 - 会議への寄与

AN - SCOPUS:0026299685

SN - 0780302273

SN - 9780780302273

T3 - 91 IEEE Int Jt Conf Neural Networks IJCNN 91

SP - 2288

EP - 2293

BT - 91 IEEE Int Jt Conf Neural Networks IJCNN 91

PB - Publ by IEEE

T2 - 1991 IEEE International Joint Conference on Neural Networks - IJCNN '91

Y2 - 18 November 1991 through 21 November 1991

ER -

A T-Model neural network with learning ability

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this