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