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 |
| 巻 | 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 12 → 1997 10 15 |
Other
| Other | Proceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 1 (of 5) |
|---|---|
| 市 | Orlando, FL, USA |
| 期間 | 97/10/12 → 97/10/15 |
Fingerprint
ASJC Scopus subject areas
- Hardware and Architecture
- Control and Systems Engineering
これを引用
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
}
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 -