Connectionists: Paper on new complex-valued neural network with derivative-free learning

[Igor Aizenberg]

Dear Connectionists,

 

I would like to announce a new paper on a new complex-valued feedforward
neural network with a highly efficient derivative-free backpropagation
learning algorithm published by the Springer's Soft Computing journal:

 

Igor Aizenberg and Claudio Moraga. "Multilayer Feedforward Neural
Network based on Multi-Valued Neurons and a Backpropagation Learning
Algorithm", Soft Computing, Vol. 11, No 2, January, 2007, pp. 169-183.

 

The paper is available at 

http://www.freewebs.com/igora/PUBLICATIONS/Soft_Computing_Aizenberg-Mora
ga_2007.pdf 

 

 

Abstract.

 

A multilayer neural network based on multi-valued neurons is considered
in the paper. 

A multi-valued neuron (MVN) is based on the principles of
multiple-valued 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 functionality of the
multi-valued neuron, it is possible to obtain a new powerful neural
network. Its training does not require a derivative of the activation
function and its functionality is higher than the functionality of MLF
containing the same number of layers and neurons. These advantages of
MLMVN are confirmed by testing using parity n, two spirals and "sonar"
benchmarks and the Mackey-Glass time series prediction.

 

Your comments are very welcome.

 

Best regards,

 

Igor

 

________________

Dr. Igor Aizenberg

Texas A&M University-Texarkana
Department of Computer and Information Sciences
P.O. Box 5518, 
2600 N. Robison Rd. Texarkana, 
Texas 75505 USA

Phone: (1 903) 223-3183; 
Fax:   (1 903) 223-3189;

Skype: igor_aizenberg

e-mail: igor.aizenberg at tamut.edu <mailto:igor.aizenberg at tamut.edu> 
        or igor.aizenberg at gmail.com <mailto:igor.aizenberg at gmail.com> 

URL:   http://www.freewebs.com/igora <http://www.freewebs.com/igora>