A modified error backpropagation algorithm for complex-value neural networks

The complex-valued backpropagation algorithm has been widely used in fields of dealing with telecommunications, speech recognition and image processing with Fourier transformation. However, the local minima problem usually occurs in the process of learning. To solve this problem and to speed up the...

Full description

Saved in:

Bibliographic Details
Published in:	International journal of neural systems Vol. 15; no. 6; p. 435
Main Authors:	Chen, Xiaoming, Tang, Zheng, Variappan, Catherine, Li, Songsong, Okada, Toshimi
Format:	Journal Article
Language:	English
Published:	Singapore 01.12.2005
Subjects:	Algorithms Artificial Intelligence Computer Simulation Learning Mathematics Neural Networks (Computer) Signal Processing, Computer-Assisted
ISSN:	0129-0657
Online Access:	Get more information
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	The complex-valued backpropagation algorithm has been widely used in fields of dealing with telecommunications, speech recognition and image processing with Fourier transformation. However, the local minima problem usually occurs in the process of learning. To solve this problem and to speed up the learning process, we propose a modified error function by adding a term to the conventional error function, which is corresponding to the hidden layer error. The simulation results show that the proposed algorithm is capable of preventing the learning from sticking into the local minima and of speeding up the learning.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	0129-0657
DOI:	10.1142/s0129065705000426