Recurrent neural networks training with stable risk-sensitive Kalman filter algorithm

Wen Yu; José De Jesús Rubio; Xiaoou Li

doi:10.1109/IJCNN.2005.1555937

Recurrent neural networks training with stable risk-sensitive Kalman filter algorithm

Wen Yu, José De Jesús Rubio, Xiaoou Li

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

4 Scopus citations

Abstract

Compared to normal learning algorithms, for example backpropagation, Kalman filter-based algorithm has some better properties, such as faster convergence. In this paper, Kalman filter is modified with a risk-sensitive cost criterion, we call it as risk-sensitive Kalman filter. This new algorithm is applied to train recurrent neural networks for nonlinear system identification. Input-to-state stability is used to prove that the risk-sensitive Kalman filter training is stable. The contributions of this paper are: 1) the risk-sensitive Kalman filter is used for the state-space recurrent neural networks training, 2) the stability of the risk-sensitive Kalman filter is proved.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005
Pages	700-705
Number of pages	6
DOIs	https://doi.org/10.1109/IJCNN.2005.1555937
State	Published - 2005
Externally published	Yes
Event	International Joint Conference on Neural Networks, IJCNN 2005 - Montreal, QC, Canada Duration: 31 Jul 2005 → 4 Aug 2005

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	2

Conference

Conference	International Joint Conference on Neural Networks, IJCNN 2005
Country/Territory	Canada
City	Montreal, QC
Period	31/07/05 → 4/08/05

Access to Document

10.1109/IJCNN.2005.1555937

Cite this

Yu, W., De Jesús Rubio, J., & Li, X. (2005). Recurrent neural networks training with stable risk-sensitive Kalman filter algorithm. In Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005 (pp. 700-705). Article 1555937 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2). https://doi.org/10.1109/IJCNN.2005.1555937

@inproceedings{ed7cfa8a34dd4cbe8e838b447cc44b91,

title = "Recurrent neural networks training with stable risk-sensitive Kalman filter algorithm",

abstract = "Compared to normal learning algorithms, for example backpropagation, Kalman filter-based algorithm has some better properties, such as faster convergence. In this paper, Kalman filter is modified with a risk-sensitive cost criterion, we call it as risk-sensitive Kalman filter. This new algorithm is applied to train recurrent neural networks for nonlinear system identification. Input-to-state stability is used to prove that the risk-sensitive Kalman filter training is stable. The contributions of this paper are: 1) the risk-sensitive Kalman filter is used for the state-space recurrent neural networks training, 2) the stability of the risk-sensitive Kalman filter is proved.",

author = "Wen Yu and {De Jes{\'u}s Rubio}, Jos{\'e} and Xiaoou Li",

year = "2005",

doi = "10.1109/IJCNN.2005.1555937",

language = "Ingl{\'e}s",

isbn = "0780390482",

series = "Proceedings of the International Joint Conference on Neural Networks",

pages = "700--705",

booktitle = "Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005",

note = "International Joint Conference on Neural Networks, IJCNN 2005 ; Conference date: 31-07-2005 Through 04-08-2005",

}

Yu, W, De Jesús Rubio, J & Li, X 2005, Recurrent neural networks training with stable risk-sensitive Kalman filter algorithm. in Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005., 1555937, Proceedings of the International Joint Conference on Neural Networks, vol. 2, pp. 700-705, International Joint Conference on Neural Networks, IJCNN 2005, Montreal, QC, Canada, 31/07/05. https://doi.org/10.1109/IJCNN.2005.1555937

Recurrent neural networks training with stable risk-sensitive Kalman filter algorithm. / Yu, Wen; De Jesús Rubio, José; Li, Xiaoou.
Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005. 2005. p. 700-705 1555937 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2).

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

TY - GEN

T1 - Recurrent neural networks training with stable risk-sensitive Kalman filter algorithm

AU - Yu, Wen

AU - De Jesús Rubio, José

AU - Li, Xiaoou

PY - 2005

Y1 - 2005

N2 - Compared to normal learning algorithms, for example backpropagation, Kalman filter-based algorithm has some better properties, such as faster convergence. In this paper, Kalman filter is modified with a risk-sensitive cost criterion, we call it as risk-sensitive Kalman filter. This new algorithm is applied to train recurrent neural networks for nonlinear system identification. Input-to-state stability is used to prove that the risk-sensitive Kalman filter training is stable. The contributions of this paper are: 1) the risk-sensitive Kalman filter is used for the state-space recurrent neural networks training, 2) the stability of the risk-sensitive Kalman filter is proved.

AB - Compared to normal learning algorithms, for example backpropagation, Kalman filter-based algorithm has some better properties, such as faster convergence. In this paper, Kalman filter is modified with a risk-sensitive cost criterion, we call it as risk-sensitive Kalman filter. This new algorithm is applied to train recurrent neural networks for nonlinear system identification. Input-to-state stability is used to prove that the risk-sensitive Kalman filter training is stable. The contributions of this paper are: 1) the risk-sensitive Kalman filter is used for the state-space recurrent neural networks training, 2) the stability of the risk-sensitive Kalman filter is proved.

UR - http://www.scopus.com/inward/record.url?scp=33745965821&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2005.1555937

DO - 10.1109/IJCNN.2005.1555937

M3 - Contribución a la conferencia

AN - SCOPUS:33745965821

SN - 0780390482

SN - 9780780390485

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 700

EP - 705

BT - Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005

T2 - International Joint Conference on Neural Networks, IJCNN 2005

Y2 - 31 July 2005 through 4 August 2005

ER -

Recurrent neural networks training with stable risk-sensitive Kalman filter algorithm

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this