Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
534 IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 17, NO. 2, MARCH 2006 Book Reviews___________________________________________________________________________
 

Summary: 534 IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 17, NO. 2, MARCH 2006
Book Reviews___________________________________________________________________________
Complex-Valued Neural Networks: Theories and Applica-
tions--A. Hirose, Ed. (NJ.: World Scientific Publishing Co. Pte. Ltd.,
2004, ISBN 0-981-238-561-4). Reviewed by I. Aizenberg
The reviewed book is devoted to the neural networks that are based
on the neurons with the complex-valued weights and complex-valued
activation functions. In recent years, these neural networks have be-
come more and more popular. A number of the original solutions in pat-
tern recognition and classification, in artificial neural information pro-
cessing, in image processing and in the theory of artificial neurons and
neural networks that are based on the use of complex-valued neurons
have been proposed. It is very important that the use of complex-valued
weights and complex-valued activation functions is not a simply theo-
retical generalization of the real-valued case, but it makes possible to
extend the functionality both of a single neuron and a network, to ob-
tain much more stable learning algorithms and finally to solve many
complicated applied problems that either cannot be solved using the
real-valued neural networks or to solve them in a simpler way and more
efficiently.

  

Source: Aizenberg, Igor - College of Science, Technology, Engineering, and Mathematics, Texas A&M University at Texarkana

 

Collections: Computer Technologies and Information Sciences