Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Abstract--In this paper, we further develop a complex-valued neuron paradigm. It is shown how a single multi-valued
 

Summary: Abstract--In this paper, we further develop a complex-
valued neuron paradigm. It is shown how a single multi-valued
neuron with a periodic activation function may learn multiple-
valued nonlinearly separable problems. One of the classical
nonlinearly separable problems mod k addition of n variables
is considered in detail. It is shown that to be able to learn this
problem using a single multi-valued neuron, it is necessary to
use a periodic activation function and a learning algorithm
based on the error-correction learning rule and adapted to this
activation function.
I. INTRODUCTION
N this paper, we concentrate on the further development of
a complex-valued neuron paradigm. In the last two
decades, complex-valued neural networks have become
increasingly popular. Using complex-valued inputs/outputs,
weights and activation functions, it is possible to increase
the functionality of a single neuron and of a neural network,
to improve their performance, and to reduce the training
time [1]. Different specific types of complex-valued neurons
and complex-valued activation functions were observed, for

  

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

 

Collections: Computer Technologies and Information Sciences