Premium
An evaluation of the bihyperbolic function in the optimization of the backpropagation algorithm
Author(s) -
Miguez Geraldo,
Xavier Adilson Elias,
Maculan Nelson
Publication year - 2014
Publication title -
international transactions in operational research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.032
H-Index - 52
eISSN - 1475-3995
pISSN - 0969-6016
DOI - 10.1111/itor.12072
Subject(s) - backpropagation , computer science , artificial neural network , set (abstract data type) , algorithm , sigmoid function , function (biology) , range (aeronautics) , artificial intelligence , rprop , machine learning , types of artificial neural networks , time delay neural network , evolutionary biology , programming language , materials science , composite material , biology
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.