|
Organizers |
Functional Learning Habitually in the multi layer perceptron (MLP) learning, we use the
back-forward algorithm to change the weights of connectors between neurons but
the activate functions stay fixed, the innocent question posed at this moment
is: why we don’t make the opposite? So that we can change the activate functions
and we fix the weights, the present paper shall discus this solution, also some
psychological phenomena as the separated learning, the continued learning and
forget, if they can artificially simulated we can construct the first model of
the electronic brain. Date received: January 19, 2010 Copyright © 2010 by the author(s). The author(s) of this document and the
organizers of the conference have granted their consent to include this abstract
in Atlas Conferences Inc. Document #
cazk-20.Introduction to the
Electronic Brain on El-dorra neural network
technology
by
Omari Abdallah
Study &
Research Center of Bioinformatics, BP 488 Adrar (RP) 01000, ALGERIA DZ