Recurrent neural network using mixture of experts for time series processing

Mirai Tabuse, Makoto Kinouchi, Masafumi Hagiwara

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

Abstract

In this paper, we propose a Mixture of Experts with recurrent connections for improved time series processing. The proposed network has recurrent connections from the output layer to the context layer as the Jordan network. The context layer is expanded to a number of sublayers so that the necessary information for time series processing can be held for longer time. Most of the learning algorithms for the conventional recurrent networks are based on the Back-Propagation (BP) algorithm so that the number of epochs required for convergence tends to increase. The Mixture of Experts used in the proposed network employs a modular approach. Trained with the Expectation-Maximization (EM) algorithm, the Mixture of Experts performs very fast convergence especially in the initial steps. The proposed network can also employ the EM algorithm so that faster convergence is expected. We have examined the ability of the proposed network by some computer simulations. It is shown that the proposed network is faster than the conventional ones in point of the number of epochs required for convergence.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Editors Anon
PublisherIEEE
Pages536-541
Number of pages6
Volume1
Publication statusPublished - 1997
EventProceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 1 (of 5) - Orlando, FL, USA
Duration: 1997 Oct 121997 Oct 15

Other

OtherProceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 1 (of 5)
CityOrlando, FL, USA
Period97/10/1297/10/15

Fingerprint

Recurrent neural networks
Time series
Processing
Backpropagation algorithms
Learning algorithms
Computer simulation

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Tabuse, M., Kinouchi, M., & Hagiwara, M. (1997). Recurrent neural network using mixture of experts for time series processing. In Anon (Ed.), Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Vol. 1, pp. 536-541). IEEE.

Recurrent neural network using mixture of experts for time series processing. / Tabuse, Mirai; Kinouchi, Makoto; Hagiwara, Masafumi.

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. ed. / Anon. Vol. 1 IEEE, 1997. p. 536-541.

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

Tabuse, M, Kinouchi, M & Hagiwara, M 1997, Recurrent neural network using mixture of experts for time series processing. in Anon (ed.), Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. vol. 1, IEEE, pp. 536-541, Proceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 1 (of 5), Orlando, FL, USA, 97/10/12.
Tabuse M, Kinouchi M, Hagiwara M. Recurrent neural network using mixture of experts for time series processing. In Anon, editor, Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 1. IEEE. 1997. p. 536-541
Tabuse, Mirai ; Kinouchi, Makoto ; Hagiwara, Masafumi. / Recurrent neural network using mixture of experts for time series processing. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. editor / Anon. Vol. 1 IEEE, 1997. pp. 536-541
@inproceedings{e6e522c88c82461b8093f581f0f60863,
title = "Recurrent neural network using mixture of experts for time series processing",
abstract = "In this paper, we propose a Mixture of Experts with recurrent connections for improved time series processing. The proposed network has recurrent connections from the output layer to the context layer as the Jordan network. The context layer is expanded to a number of sublayers so that the necessary information for time series processing can be held for longer time. Most of the learning algorithms for the conventional recurrent networks are based on the Back-Propagation (BP) algorithm so that the number of epochs required for convergence tends to increase. The Mixture of Experts used in the proposed network employs a modular approach. Trained with the Expectation-Maximization (EM) algorithm, the Mixture of Experts performs very fast convergence especially in the initial steps. The proposed network can also employ the EM algorithm so that faster convergence is expected. We have examined the ability of the proposed network by some computer simulations. It is shown that the proposed network is faster than the conventional ones in point of the number of epochs required for convergence.",
author = "Mirai Tabuse and Makoto Kinouchi and Masafumi Hagiwara",
year = "1997",
language = "English",
volume = "1",
pages = "536--541",
editor = "Anon",
booktitle = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",
publisher = "IEEE",

}

TY - GEN

T1 - Recurrent neural network using mixture of experts for time series processing

AU - Tabuse, Mirai

AU - Kinouchi, Makoto

AU - Hagiwara, Masafumi

PY - 1997

Y1 - 1997

N2 - In this paper, we propose a Mixture of Experts with recurrent connections for improved time series processing. The proposed network has recurrent connections from the output layer to the context layer as the Jordan network. The context layer is expanded to a number of sublayers so that the necessary information for time series processing can be held for longer time. Most of the learning algorithms for the conventional recurrent networks are based on the Back-Propagation (BP) algorithm so that the number of epochs required for convergence tends to increase. The Mixture of Experts used in the proposed network employs a modular approach. Trained with the Expectation-Maximization (EM) algorithm, the Mixture of Experts performs very fast convergence especially in the initial steps. The proposed network can also employ the EM algorithm so that faster convergence is expected. We have examined the ability of the proposed network by some computer simulations. It is shown that the proposed network is faster than the conventional ones in point of the number of epochs required for convergence.

AB - In this paper, we propose a Mixture of Experts with recurrent connections for improved time series processing. The proposed network has recurrent connections from the output layer to the context layer as the Jordan network. The context layer is expanded to a number of sublayers so that the necessary information for time series processing can be held for longer time. Most of the learning algorithms for the conventional recurrent networks are based on the Back-Propagation (BP) algorithm so that the number of epochs required for convergence tends to increase. The Mixture of Experts used in the proposed network employs a modular approach. Trained with the Expectation-Maximization (EM) algorithm, the Mixture of Experts performs very fast convergence especially in the initial steps. The proposed network can also employ the EM algorithm so that faster convergence is expected. We have examined the ability of the proposed network by some computer simulations. It is shown that the proposed network is faster than the conventional ones in point of the number of epochs required for convergence.

UR - http://www.scopus.com/inward/record.url?scp=0031357930&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031357930&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0031357930

VL - 1

SP - 536

EP - 541

BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

A2 - Anon, null

PB - IEEE

ER -