An Accelerating Method of Training Neural Networks Based on Vector Epsilon Algorithm

Author

Li, Jianliang ; Lian, Lian ; Jiang, Yong

Author_Institution

Sch. of Sci., Nanjing Univ. of Sci. & Technol., Nanjing, China

Volume

4

fYear

2010

fDate

4-6 June 2010

Firstpage

292

Lastpage

295

Abstract

This paper studied the accelerating convergence of the vector sequences generated by BP algorithm with vector epsilon algorithm, and presented the conclusion that the algorithms is not only convergent but also accelerated. Finally, we tested them for three classical artificial neural network problems. By numerical experiments, results shown that can reduce CPU time for computation and improve the learning efficiency.

Keywords

backpropagation; convergence; feedforward neural nets; learning (artificial intelligence); sequences; vectors; BP algorithm; CPU; accelerating convergence; artificial neural network; computation time; vector epsilon algorithm; vector sequence; Acceleration; Artificial neural networks; Computer networks; Feedforward neural networks; Feedforward systems; Feeds; Gradient methods; Iterative algorithms; Multi-layer neural network; Neural networks; BP algorithm; accelerated convergence; artificial neural networks; epsilon algorithm; numerical analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Information and Computing (ICIC), 2010 Third International Conference on

Conference_Location

Wuxi, Jiang Su

Print_ISBN

978-1-4244-7081-5

Electronic_ISBN

978-1-4244-7082-2

Type

conf

DOI

10.1109/ICIC.2010.345

Filename

5514077