|
Once the behaviour of particular brain circuits has been analyzed, we have added up some of these patterns to Artificial Neural Networks; thus anew hybrid learning method has emeged. In order to find the best solution to a give problem, this method combines the use of Genetic Algotithms with particular changes to connection weights based in the behaviour observed in the brain circuits analyzed. The design and implementation of this combination is shown in feed-forward multiplayer artificial neural networks, specifically created to solve a simple problem. We also illustrate the benefits obtained with these new nets from a comparison with previos results achived by the optimal Artificial Neural Networks used so far for solving the same problem.
|