how can i use genetic algorithm to teain preceptron

Hi all;

how can i use genetic algorithm to teain Perceptrons?

Answer 1

[Timothy Felty]

If you have a genetic algorithm already, the easiest way is to make the weights the chromosomes, and then use the error of the perceptron as the goal function. When error is less than your desired threshold freeze the best individual as the weights.

If you have different possible activation functions you could include them in the chromosomes and have the GA find that as well.

[mohammed]

I have Perceptron algorthim,

could you help me to add GA for training

=================

inputs = xlsread('data1.xls', 1, 'A2:D115');

inputs=inputs';

targets = xlsread('data1.xls', 1, 'L2:L115');

targets = targets';

numHiddenNeurons = 20; % Adjust as desired

net = newpr(inputs,targets,numHiddenNeurons);

net.divideParam.trainRatio = 70/100; % Adjust as desired

net.divideParam.valRatio = 15/100; % Adjust as desired

net.divideParam.testRatio = 15/100; % Adjust as desired

net.trainParam.epochs= 1000;

net.trainParam.goal=0.01;

net.adaptFcn= 'trains';

% Train and Apply Network

net.trainFcn= 'trainbr';%'trainbfg''trainbr';'trainlm';

[net,tr] = train(net,inputs,targets);

outputs = sim(net,inputs);

=================