An evaluation of the bihyperbolic function in the optimization of the backpropagation algorithm

The backpropagation algorithm is one of the most used tools for training artificial neural networks. However, this tool may be very slow in some practical applications. Many techniques have been discussed to speed up the performance of this algorithm and allow its use in an even broader range of app...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:International transactions in operational research Ročník 21; číslo 5; s. 835 - 854
Hlavní autori: Miguez, Geraldo, Xavier, Adilson Elias, Maculan, Nelson
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Oxford Blackwell Publishing Ltd 01.09.2014
Predmet:
activation function
Algorithms
Back propagation
backpropagation algorithm
bihyperbolic function
Computation
Discrimination
machine learning
Mathematical analysis
Mathematical models
Neural networks
Operational research
Operations research
Optimization
pattern recognition
Studies
ISSN:0969-6016, 1475-3995
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The backpropagation algorithm is one of the most used tools for training artificial neural networks. However, this tool may be very slow in some practical applications. Many techniques have been discussed to speed up the performance of this algorithm and allow its use in an even broader range of applications. Although the backpropagation algorithm has been used for decades, we present here a set of computational results that suggest that by replacing bihyperbolic functions the backpropagation algorithm performs better than the traditional sigmoid functions. To the best of our knowledge, this finding was never previously published in the open literature. The efficiency and discrimination capacity of the proposed methodology are shown through a set of computational experiments, and compared with the traditional problems of the literature.
Bibliografia:ark:/67375/WNG-ZFF6VQCX-P
istex:1C02B9F1A109043CA5549BED5DC7A6F8EFF10AA7
ArticleID:ITOR12072
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ISSN:0969-6016
1475-3995
DOI:10.1111/itor.12072