0
$\begingroup$

How does innovation deal with the problem of different connections in NEAT? An example makes it clearer: the neural network has two outputs 3 and 4, they are connected according to the scheme 10 -> 6 -> 3, 11 -> 7 -> 4, there is another neural network which has 10 -> 6 -> 4, 11 -> 7 -> 3. It turns out that here 10 -> 6 is responsible for different outputs, how does innovation in NEAT cope with this?

Improve this question
$\endgroup$

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.