Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Training feed-forward neural networks using the gradient descent method with the optimal stepsize
State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University.
State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University.
State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University.
Luleå University of Technology, Department of Civil, Environmental and Natural Resources Engineering, Operation, Maintenance and Acoustics.
2012 (English)In: Journal of Computational Information Systems, ISSN 1553-9105, Vol. 8, no 4, 1359-1371 p.Article in journal (Refereed) Published
Abstract [en]

The most widely used algorithm for training multiplayer feedforward networks, Error BackPropagation (EBP), is an iterative gradient descend algorithm by nature. Variable stepsize is the key to fast convergence of BP networks. A new optimal stepsize algorithm is proposed for accelerating the training process. It modifies the objective function to reduce the computational complexity of the Jacobin and consequently that of Hessian matrices, and hereby directly computes the optimal iterative stepsize. The improved backpropagation algorithm helps alleviating the problem of slow convergence and oscillations. The analysis indicates that the backpropagation with optimal stepsize (BPOS) is more efficient when treating large-scale samples. The numerical experiment results on pattern recognition and function approximation problems show that the proposed algorithm possesses the features of fast convergence and less intensive computational complexity.

Place, publisher, year, edition, pages
2012. Vol. 8, no 4, 1359-1371 p.
National Category
Other Civil Engineering
Research subject
Operation and Maintenance
Identifiers
URN: urn:nbn:se:ltu:diva-8599Local ID: 71e87e73-f977-4680-a137-32b843648626OAI: oai:DiVA.org:ltu-8599DiVA: diva2:981537
Note
Godkänd; 2012; 20120420 (andbra)Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2017-11-24Bibliographically approved

Open Access in DiVA

fulltext(509 kB)76 downloads
File information
File name FULLTEXT01.pdfFile size 509 kBChecksum SHA-512
a80a8432665a8cf19f4c1dae390faa4812c6f6a315085343a2125684695deb83eacbaeac6a73ca144fce8bacf3b1e2d434cad1a510d98578cf8e78c64ffab37c
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Fuqing, Yuan
By organisation
Operation, Maintenance and Acoustics
Other Civil Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 76 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 52 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf