BRAIN Journal-High Performance Data mining by Genetic Neural Network-Figure 8 . The Comparision of Run Times

That is distinct that dynamic mutation rate or reduction idea for mutation operator is more
better of fixed rate. In fact obtain to high accuracy is result of our idea for mutation operator.
The number of hidden layer neurone is important problem for NN. The natural selection by
GA help finding the number of hidden layer neurone and it progress on duration generations.
The structured model of GANN finds better answer than NN but with much run time in
simulation. The learning of GA is much better than NN with back propagation because BP is a
method based on gradient descend and local optimum is a serious risk for that.
We hope that the number of training samples is more accurate without error, the new
algorithm is better. Tests show that the combination of genetic algorithms and neural networks to an
acceptable level solves the problem of overfitting.