Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Soft Comput (2007) 11: 169183 DOI 10.1007/s00500-006-0075-5

Summary: Soft Comput (2007) 11: 169183
DOI 10.1007/s00500-006-0075-5
Igor Aizenberg Claudio Moraga
Multilayer feedforward neural network based on multi-valued
neurons (MLMVN) and a backpropagation learning algorithm
Published online: 20 April 2006
Springer-Verlag 2006
Abstract Amultilayerneuralnetworkbasedonmulti-valued
neurons (MLMVN) is considered in the paper. A multi-val-
ued neuron (MVN) is based on the principles of multiple-val-
ued threshold logic over the field of the complex numbers.
The most important properties of MVN are: the complex-
valued weights, inputs and output coded by the kth roots of
unity and the activation function, which maps the complex
plane into the unit circle. MVN learning is reduced to the
movement along the unit circle, it is based on a simple linear
error correction rule and it does not require a derivative. It
is shown that using a traditional architecture of multilayer
feedforward neural network (MLF) and the high function-


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


Collections: Computer Technologies and Information Sciences