### 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 language | English |
---|---|

Title of host publication | Proceedings of the IEEE International Conference on Systems, Man and Cybernetics |

Editors | Anon |

Publisher | IEEE |

Pages | 536-541 |

Number of pages | 6 |

Volume | 1 |

Publication status | Published - 1997 |

Event | Proceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 1 (of 5) - Orlando, FL, USA Duration: 1997 Oct 12 → 1997 Oct 15 |

### Other

Other | Proceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 1 (of 5) |
---|---|

City | Orlando, FL, USA |

Period | 97/10/12 → 97/10/15 |

### Fingerprint

### ASJC Scopus subject areas

- Hardware and Architecture
- Control and Systems Engineering

### Cite this

*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.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*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.

}

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 -