Geek Answers Handbook

Using a genetic algorithm, how can I create offspring based on two neural network structures?

I have two arrays of objects that describe the structure of a neural network, how can I combine them to create realistic offspring? Chromosomes look something like this:

chromosome = [
    [Node, Node, Node],
    [Node, Node, Node, Node, Node],
    [Node, Node, Node, Node],
    [Node, Node, Node, Node, Node],
    [Node, Node, Node, Node, Node, Node, Node],
    [Node, Node, Node],
];

Node example:

Node {
    nodesThatThisIsConnectedTo = [0, 2, 3, 5] // These numbers identify which nodes to collect output from in the preceding layer from based on their index number
    weights = [0.34, 0.33, 0.76, -0.56] // These are the corresponding weights applied to the mentioned nodes
}
+5
source share
1 answer

I think the best approach would be to implement a genetic algorithm search for each weight vector node - if you are locked when using GA.

node , node . , , .

0

More articles:


All Articles