A New Modified Hybrid Learning Algorithm for Feedforward Neural Networks

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

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-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 languageEnglish
Title of host publicationAdvances in Neural Networks - ISNN 2005
Subtitle of host publicationSecond International Symposium on Neural Networks, Chongqing, China, May 30 - June 1, 2005, Proceedings, Part I
EditorsJun Wang, Xiaofeng Liao, Zhang Yi
Place of PublicationBerlin, Heidelberg
PublisherSpringer
Pages572-577
Number of pages6
Edition1st
ISBN (Electronic)9783540320654
ISBN (Print)9783540259121
DOIs
Publication statusPublished - 2 May 2005
EventSecond International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005 - Chongqing, China
Duration: 30 May 20051 Jun 2005
https://link.springer.com/book/10.1007/b136476

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameTheoretical Computer Science and General Issues
NameISNN: International Symposium on Neural Networks

Conference

ConferenceSecond International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005
Country/TerritoryChina
CityChongqing
Period30/05/051/06/05
Internet address

Scopus Subject Areas

  • Theoretical Computer Science
  • Computer Science(all)

User-Defined Keywords

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

Fingerprint

Dive into the research topics of 'A New Modified Hybrid Learning Algorithm for Feedforward Neural Networks'. Together they form a unique fingerprint.

Cite this