A New Modified Hybrid Learning Algorithm for Feedforward Neural Networks

Fei Han; Deshuang Huang; Yiu Ming Cheung; Guangbin Huang

doi:10.1007/11427391_91

A New Modified Hybrid Learning Algorithm for Feedforward Neural Networks

Fei Han^*, Deshuang Huang, Yiu Ming Cheung, Guangbin Huang

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

10 Citations (Scopus)

Abstract

In this paper, a new modified hybrid learning algorithm for feedforward neural networks is proposed to obtain better generalization performance. For the sake of penalizing both the input-to-output mapping sensitivity and the high frequency components in training data, the first additional cost term and the second one are selected based on the first-order derivatives of the neural activation at the hidden layers and the second-order derivatives of the neural activation at the output layer, respectively. Finally, theoretical justifications and simulation results are given to verify the efficiency and effectiveness of our proposed learning algorithm.

Original language	English
Title of host publication	Advances in Neural Networks - ISNN 2005
Subtitle of host publication	Second International Symposium on Neural Networks, Chongqing, China, May 30 - June 1, 2005, Proceedings, Part I
Editors	Jun Wang, Xiaofeng Liao, Zhang Yi
Place of Publication	Berlin, Heidelberg
Publisher	Springer
Pages	572-577
Number of pages	6
Edition	1st
ISBN (Electronic)	9783540320654
ISBN (Print)	9783540259121
DOIs	https://doi.org/10.1007/11427391_91
Publication status	Published - 2 May 2005
Event	Second International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005 - Chongqing, China Duration: 30 May 2005 → 1 Jun 2005 https://link.springer.com/book/10.1007/b136476

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Name	Theoretical Computer Science and General Issues

Name	ISNN: International Symposium on Neural Networks

Conference

Conference	Second International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005
Country/Territory	China
City	Chongqing
Period	30/05/05 → 1/06/05
Internet address	https://link.springer.com/book/10.1007/b136476

User-Defined Keywords

Hide Layer
Output Layer
Feedforward Neural Network
High Frequency Component
Modify Algorithm

Access to Document

10.1007/11427391_91

Cite this

Han, F., Huang, D., Cheung, Y. M., & Huang, G. (2005). A New Modified Hybrid Learning Algorithm for Feedforward Neural Networks. In J. Wang, X. Liao, & Z. Yi (Eds.), Advances in Neural Networks - ISNN 2005: Second International Symposium on Neural Networks, Chongqing, China, May 30 - June 1, 2005, Proceedings, Part I (1st ed., pp. 572-577). (Lecture Notes in Computer Science), (Theoretical Computer Science and General Issues), (ISNN: International Symposium on Neural Networks). Springer. https://doi.org/10.1007/11427391_91

Han, Fei ; Huang, Deshuang ; Cheung, Yiu Ming et al. / A New Modified Hybrid Learning Algorithm for Feedforward Neural Networks. Advances in Neural Networks - ISNN 2005: Second International Symposium on Neural Networks, Chongqing, China, May 30 - June 1, 2005, Proceedings, Part I. editor / Jun Wang ; Xiaofeng Liao ; Zhang Yi. 1st. ed. Berlin, Heidelberg : Springer, 2005. pp. 572-577 (Lecture Notes in Computer Science). (Theoretical Computer Science and General Issues). (ISNN: International Symposium on Neural Networks).

@inproceedings{04dc97c733c44e66939c605972010179,

title = "A New Modified Hybrid Learning Algorithm for Feedforward Neural Networks",

abstract = "In this paper, a new modified hybrid learning algorithm for feedforward neural networks is proposed to obtain better generalization performance. For the sake of penalizing both the input-to-output mapping sensitivity and the high frequency components in training data, the first additional cost term and the second one are selected based on the first-order derivatives of the neural activation at the hidden layers and the second-order derivatives of the neural activation at the output layer, respectively. Finally, theoretical justifications and simulation results are given to verify the efficiency and effectiveness of our proposed learning algorithm.",

keywords = "Hide Layer, Output Layer, Feedforward Neural Network, High Frequency Component, Modify Algorithm",

author = "Fei Han and Deshuang Huang and Cheung, {Yiu Ming} and Guangbin Huang",

note = "Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; Second International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005 ; Conference date: 30-05-2005 Through 01-06-2005",

year = "2005",

month = may,

day = "2",

doi = "10.1007/11427391_91",

language = "English",

isbn = "9783540259121",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "572--577",

editor = "Jun Wang and Xiaofeng Liao and Zhang Yi",

booktitle = "Advances in Neural Networks - ISNN 2005",

edition = "1st",

url = "https://link.springer.com/book/10.1007/b136476",

}

Han, F, Huang, D, Cheung, YM & Huang, G 2005, A New Modified Hybrid Learning Algorithm for Feedforward Neural Networks. in J Wang, X Liao & Z Yi (eds), Advances in Neural Networks - ISNN 2005: Second International Symposium on Neural Networks, Chongqing, China, May 30 - June 1, 2005, Proceedings, Part I. 1st edn, Lecture Notes in Computer Science, Theoretical Computer Science and General Issues, ISNN: International Symposium on Neural Networks, Springer, Berlin, Heidelberg, pp. 572-577, Second International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005, Chongqing, China, 30/05/05. https://doi.org/10.1007/11427391_91

A New Modified Hybrid Learning Algorithm for Feedforward Neural Networks. / Han, Fei; Huang, Deshuang; Cheung, Yiu Ming et al.
Advances in Neural Networks - ISNN 2005: Second International Symposium on Neural Networks, Chongqing, China, May 30 - June 1, 2005, Proceedings, Part I. ed. / Jun Wang; Xiaofeng Liao; Zhang Yi. 1st. ed. Berlin, Heidelberg: Springer, 2005. p. 572-577 (Lecture Notes in Computer Science), (Theoretical Computer Science and General Issues), (ISNN: International Symposium on Neural Networks).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - A New Modified Hybrid Learning Algorithm for Feedforward Neural Networks

AU - Han, Fei

AU - Huang, Deshuang

AU - Cheung, Yiu Ming

AU - Huang, Guangbin

PY - 2005/5/2

Y1 - 2005/5/2

N2 - In this paper, a new modified hybrid learning algorithm for feedforward neural networks is proposed to obtain better generalization performance. For the sake of penalizing both the input-to-output mapping sensitivity and the high frequency components in training data, the first additional cost term and the second one are selected based on the first-order derivatives of the neural activation at the hidden layers and the second-order derivatives of the neural activation at the output layer, respectively. Finally, theoretical justifications and simulation results are given to verify the efficiency and effectiveness of our proposed learning algorithm.

AB - In this paper, a new modified hybrid learning algorithm for feedforward neural networks is proposed to obtain better generalization performance. For the sake of penalizing both the input-to-output mapping sensitivity and the high frequency components in training data, the first additional cost term and the second one are selected based on the first-order derivatives of the neural activation at the hidden layers and the second-order derivatives of the neural activation at the output layer, respectively. Finally, theoretical justifications and simulation results are given to verify the efficiency and effectiveness of our proposed learning algorithm.

KW - Hide Layer

KW - Output Layer

KW - Feedforward Neural Network

KW - High Frequency Component

KW - Modify Algorithm

UR - http://www.scopus.com/inward/record.url?scp=24944471896&partnerID=8YFLogxK

U2 - 10.1007/11427391_91

DO - 10.1007/11427391_91

M3 - Conference proceeding

AN - SCOPUS:24944471896

SN - 9783540259121

T3 - Lecture Notes in Computer Science

SP - 572

EP - 577

BT - Advances in Neural Networks - ISNN 2005

A2 - Wang, Jun

A2 - Liao, Xiaofeng

A2 - Yi, Zhang

PB - Springer

CY - Berlin, Heidelberg

T2 - Second International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005

Y2 - 30 May 2005 through 1 June 2005

ER -

Han F, Huang D, Cheung YM, Huang G. A New Modified Hybrid Learning Algorithm for Feedforward Neural Networks. In Wang J, Liao X, Yi Z, editors, Advances in Neural Networks - ISNN 2005: Second International Symposium on Neural Networks, Chongqing, China, May 30 - June 1, 2005, Proceedings, Part I. 1st ed. Berlin, Heidelberg: Springer. 2005. p. 572-577. (Lecture Notes in Computer Science). (Theoretical Computer Science and General Issues). (ISNN: International Symposium on Neural Networks). doi: 10.1007/11427391_91

A New Modified Hybrid Learning Algorithm for Feedforward Neural Networks

Abstract

Publication series

Conference

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this