Incorporating a priori knowledge into initialized weights for neural classifier

Zhe Chen; T.J. Feng; Tian-Jin Feng; Z. Houkes

doi:10.1109/IJCNN.2000.857911

Incorporating a priori knowledge into initialized weights for neural classifier

Zhe Chen, T.J. Feng, Tian-Jin Feng, Z. Houkes

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

7 Citations (Scopus)

64 Downloads (Pure)

Abstract

Artificial neural networks (ANN), especially, multilayer perceptrons (MLP) have been widely used in pattern recognition and classification. Nevertheless, how to incorporate a priori knowledge in the design of ANNs is still an open problem. The paper tries to give some insight on this topic emphasizing weight initialization from three perspectives. Theoretical analyses and simulations are offered for validation

Original language	Undefined
Title of host publication	Proceedings of the IEEE-INNS-ENNS Int.Joint Conference on Neural Networks, Vol II
Place of Publication	Como, Italy
Publisher	IEEE
Pages	291-296
ISBN (Print)	0-7695-0619-4
DOIs	https://doi.org/10.1109/IJCNN.2000.857911
Publication status	Published - 24 Jul 2000
Event	2000 IEEE-INNS-ENNS International Joint Conference on Neural Networks, IJCNN 2000: Neural Computing: New Challenges and Perspectives for the New Millennium - Como, Italy Duration: 24 Jul 2000 → 27 Jul 2000

Publication series

Name
Publisher	IEEE Press
Volume	2

Conference

Conference	2000 IEEE-INNS-ENNS International Joint Conference on Neural Networks, IJCNN 2000
Abbreviated title	IJCNN
Country	Italy
City	Como
Period	24/07/00 → 27/07/00

Keywords

IR-16331
METIS-113216

Access to Document

10.1109/IJCNN.2000.857911

Chen00incorporating
open

Cite this

Chen, Z., Feng, T. J., Feng, T-J., & Houkes, Z. (2000). Incorporating a priori knowledge into initialized weights for neural classifier. In Proceedings of the IEEE-INNS-ENNS Int.Joint Conference on Neural Networks, Vol II (pp. 291-296). Como, Italy: IEEE. https://doi.org/10.1109/IJCNN.2000.857911

@inproceedings{3744c259740f4d8ab4038ec535b813ec,

title = "Incorporating a priori knowledge into initialized weights for neural classifier",

abstract = "Artificial neural networks (ANN), especially, multilayer perceptrons (MLP) have been widely used in pattern recognition and classification. Nevertheless, how to incorporate a priori knowledge in the design of ANNs is still an open problem. The paper tries to give some insight on this topic emphasizing weight initialization from three perspectives. Theoretical analyses and simulations are offered for validation",

keywords = "IR-16331, METIS-113216",

author = "Zhe Chen and T.J. Feng and Tian-Jin Feng and Z. Houkes",

year = "2000",

month = "7",

day = "24",

doi = "10.1109/IJCNN.2000.857911",

language = "Undefined",

isbn = "0-7695-0619-4",

publisher = "IEEE",

pages = "291--296",

booktitle = "Proceedings of the IEEE-INNS-ENNS Int.Joint Conference on Neural Networks, Vol II",

address = "United States",

}

Chen, Z, Feng, TJ, Feng, T-J & Houkes, Z 2000, Incorporating a priori knowledge into initialized weights for neural classifier. in Proceedings of the IEEE-INNS-ENNS Int.Joint Conference on Neural Networks, Vol II. IEEE, Como, Italy, pp. 291-296, 2000 IEEE-INNS-ENNS International Joint Conference on Neural Networks, IJCNN 2000, Como, Italy, 24/07/00. https://doi.org/10.1109/IJCNN.2000.857911

Incorporating a priori knowledge into initialized weights for neural classifier. / Chen, Zhe; Feng, T.J.; Feng, Tian-Jin; Houkes, Z.

Proceedings of the IEEE-INNS-ENNS Int.Joint Conference on Neural Networks, Vol II. Como, Italy : IEEE, 2000. p. 291-296.

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

TY - GEN

T1 - Incorporating a priori knowledge into initialized weights for neural classifier

AU - Chen, Zhe

AU - Feng, T.J.

AU - Feng, Tian-Jin

AU - Houkes, Z.

PY - 2000/7/24

Y1 - 2000/7/24

N2 - Artificial neural networks (ANN), especially, multilayer perceptrons (MLP) have been widely used in pattern recognition and classification. Nevertheless, how to incorporate a priori knowledge in the design of ANNs is still an open problem. The paper tries to give some insight on this topic emphasizing weight initialization from three perspectives. Theoretical analyses and simulations are offered for validation

AB - Artificial neural networks (ANN), especially, multilayer perceptrons (MLP) have been widely used in pattern recognition and classification. Nevertheless, how to incorporate a priori knowledge in the design of ANNs is still an open problem. The paper tries to give some insight on this topic emphasizing weight initialization from three perspectives. Theoretical analyses and simulations are offered for validation

KW - IR-16331

KW - METIS-113216

U2 - 10.1109/IJCNN.2000.857911

DO - 10.1109/IJCNN.2000.857911

M3 - Conference contribution

SN - 0-7695-0619-4

SP - 291

EP - 296

BT - Proceedings of the IEEE-INNS-ENNS Int.Joint Conference on Neural Networks, Vol II

PB - IEEE

CY - Como, Italy

ER -