Feed-forward neural network with adaptive buffer length

Akihiro Tsunoda, Masafumi Hagiwara, Masao Nakagawa

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

Abstract

Summary form only given, as follows. A feedforward neural network with adaptive buffer length (FAB) was proposed and simulated. FAB has some buffers that store the past inputs and switches between the buffers and hidden units, which control the output of the buffers. Computer simulation results indicate that FAB can adjust the length of buffers for each input pattern automatically. FAB can also find the Markov dimension of the input sequences more effectively than the conventional dynamic network models.

Original languageEnglish
Title of host publicationProceedings. IJCNN - International Joint Conference on Neural Networks
Editors Anon
PublisherPubl by IEEE
Pages971
Number of pages1
ISBN (Print)0780301641
Publication statusPublished - 1992
Externally publishedYes
EventInternational Joint Conference on Neural Networks - IJCNN-91-Seattle - Seattle, WA, USA
Duration: 1991 Jul 81991 Jul 12

Other

OtherInternational Joint Conference on Neural Networks - IJCNN-91-Seattle
CitySeattle, WA, USA
Period91/7/891/7/12

Fingerprint

Feedforward neural networks
Switches
Computer simulation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Tsunoda, A., Hagiwara, M., & Nakagawa, M. (1992). Feed-forward neural network with adaptive buffer length. In Anon (Ed.), Proceedings. IJCNN - International Joint Conference on Neural Networks (pp. 971). Publ by IEEE.

Feed-forward neural network with adaptive buffer length. / Tsunoda, Akihiro; Hagiwara, Masafumi; Nakagawa, Masao.

Proceedings. IJCNN - International Joint Conference on Neural Networks. ed. / Anon. Publ by IEEE, 1992. p. 971.

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

Tsunoda, A, Hagiwara, M & Nakagawa, M 1992, Feed-forward neural network with adaptive buffer length. in Anon (ed.), Proceedings. IJCNN - International Joint Conference on Neural Networks. Publ by IEEE, pp. 971, International Joint Conference on Neural Networks - IJCNN-91-Seattle, Seattle, WA, USA, 91/7/8.
Tsunoda A, Hagiwara M, Nakagawa M. Feed-forward neural network with adaptive buffer length. In Anon, editor, Proceedings. IJCNN - International Joint Conference on Neural Networks. Publ by IEEE. 1992. p. 971
Tsunoda, Akihiro ; Hagiwara, Masafumi ; Nakagawa, Masao. / Feed-forward neural network with adaptive buffer length. Proceedings. IJCNN - International Joint Conference on Neural Networks. editor / Anon. Publ by IEEE, 1992. pp. 971
@inproceedings{c5dee9d309024eeeb7992812b9c8611e,
title = "Feed-forward neural network with adaptive buffer length",
abstract = "Summary form only given, as follows. A feedforward neural network with adaptive buffer length (FAB) was proposed and simulated. FAB has some buffers that store the past inputs and switches between the buffers and hidden units, which control the output of the buffers. Computer simulation results indicate that FAB can adjust the length of buffers for each input pattern automatically. FAB can also find the Markov dimension of the input sequences more effectively than the conventional dynamic network models.",
author = "Akihiro Tsunoda and Masafumi Hagiwara and Masao Nakagawa",
year = "1992",
language = "English",
isbn = "0780301641",
pages = "971",
editor = "Anon",
booktitle = "Proceedings. IJCNN - International Joint Conference on Neural Networks",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Feed-forward neural network with adaptive buffer length

AU - Tsunoda, Akihiro

AU - Hagiwara, Masafumi

AU - Nakagawa, Masao

PY - 1992

Y1 - 1992

N2 - Summary form only given, as follows. A feedforward neural network with adaptive buffer length (FAB) was proposed and simulated. FAB has some buffers that store the past inputs and switches between the buffers and hidden units, which control the output of the buffers. Computer simulation results indicate that FAB can adjust the length of buffers for each input pattern automatically. FAB can also find the Markov dimension of the input sequences more effectively than the conventional dynamic network models.

AB - Summary form only given, as follows. A feedforward neural network with adaptive buffer length (FAB) was proposed and simulated. FAB has some buffers that store the past inputs and switches between the buffers and hidden units, which control the output of the buffers. Computer simulation results indicate that FAB can adjust the length of buffers for each input pattern automatically. FAB can also find the Markov dimension of the input sequences more effectively than the conventional dynamic network models.

UR - http://www.scopus.com/inward/record.url?scp=0026679054&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026679054&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026679054

SN - 0780301641

SP - 971

BT - Proceedings. IJCNN - International Joint Conference on Neural Networks

A2 - Anon, null

PB - Publ by IEEE

ER -