Learning temporal sequences by complex neurons with local feedback

Makoto Kinouchi, Masafumi Hagiwara

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

9 Citations (Scopus)

Abstract

To deal with temporal sequences is very important and difficult problem for applications of neural networks. In this paper, we propose a Multilayer Network using Complex neurons with local Feedback (MNCF). A complex neuron can keep previous information by the phase component. We derive simple learning algorithm based on the back-propagation for temporal sequences. It is shown in computer simulations that the proposed network has better ability than the conventional real ones, including Elman's network.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
PublisherIEEE
Pages3165-3169
Number of pages5
Volume6
Publication statusPublished - 1995
EventProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) - Perth, Aust
Duration: 1995 Nov 271995 Dec 1

Other

OtherProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)
CityPerth, Aust
Period95/11/2795/12/1

Fingerprint

Neurons
Feedback
Complex networks
Backpropagation
Learning algorithms
Multilayers
Neural networks
Computer simulation

ASJC Scopus subject areas

  • Software

Cite this

Kinouchi, M., & Hagiwara, M. (1995). Learning temporal sequences by complex neurons with local feedback. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 6, pp. 3165-3169). IEEE.

Learning temporal sequences by complex neurons with local feedback. / Kinouchi, Makoto; Hagiwara, Masafumi.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 6 IEEE, 1995. p. 3165-3169.

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

Kinouchi, M & Hagiwara, M 1995, Learning temporal sequences by complex neurons with local feedback. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 6, IEEE, pp. 3165-3169, Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, 95/11/27.
Kinouchi M, Hagiwara M. Learning temporal sequences by complex neurons with local feedback. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 6. IEEE. 1995. p. 3165-3169
Kinouchi, Makoto ; Hagiwara, Masafumi. / Learning temporal sequences by complex neurons with local feedback. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 6 IEEE, 1995. pp. 3165-3169
@inproceedings{5f8947b248d74fbc950c21600f1e36da,
title = "Learning temporal sequences by complex neurons with local feedback",
abstract = "To deal with temporal sequences is very important and difficult problem for applications of neural networks. In this paper, we propose a Multilayer Network using Complex neurons with local Feedback (MNCF). A complex neuron can keep previous information by the phase component. We derive simple learning algorithm based on the back-propagation for temporal sequences. It is shown in computer simulations that the proposed network has better ability than the conventional real ones, including Elman's network.",
author = "Makoto Kinouchi and Masafumi Hagiwara",
year = "1995",
language = "English",
volume = "6",
pages = "3165--3169",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Learning temporal sequences by complex neurons with local feedback

AU - Kinouchi, Makoto

AU - Hagiwara, Masafumi

PY - 1995

Y1 - 1995

N2 - To deal with temporal sequences is very important and difficult problem for applications of neural networks. In this paper, we propose a Multilayer Network using Complex neurons with local Feedback (MNCF). A complex neuron can keep previous information by the phase component. We derive simple learning algorithm based on the back-propagation for temporal sequences. It is shown in computer simulations that the proposed network has better ability than the conventional real ones, including Elman's network.

AB - To deal with temporal sequences is very important and difficult problem for applications of neural networks. In this paper, we propose a Multilayer Network using Complex neurons with local Feedback (MNCF). A complex neuron can keep previous information by the phase component. We derive simple learning algorithm based on the back-propagation for temporal sequences. It is shown in computer simulations that the proposed network has better ability than the conventional real ones, including Elman's network.

UR - http://www.scopus.com/inward/record.url?scp=0029548014&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029548014&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029548014

VL - 6

SP - 3165

EP - 3169

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

ER -