Recurrent neural network using mixture of experts for time series processing

Mirai Tabuse, Makoto Kinouchi, Masafumi Hagiwara

研究成果: Conference contribution

抄録

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.

元の言語English
ホスト出版物のタイトルProceedings of the IEEE International Conference on Systems, Man and Cybernetics
編集者 Anon
出版者IEEE
ページ536-541
ページ数6
1
出版物ステータスPublished - 1997
イベントProceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 1 (of 5) - Orlando, FL, USA
継続期間: 1997 10 121997 10 15

Other

OtherProceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 1 (of 5)
Orlando, FL, USA
期間97/10/1297/10/15

Fingerprint

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

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

これを引用

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

研究成果: Conference contribution

Tabuse, M, Kinouchi, M & Hagiwara, M 1997, Recurrent neural network using mixture of experts for time series processing. : Anon (版), Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. 巻. 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. : Anon, 編集者, Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. 巻 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. 編集者 / Anon. 巻 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 -