MATLAB Answers


finding optimal neural network architecture using genetic algorithms

Asked by hüsnü alay on 25 Feb 2019
Latest activity Edited by hüsnü alay on 26 Feb 2019
I am working on a project and i need to use genetic algorithm to find number of neurons and hidden layers for neural network. I dont know how i can do it. Can you help me for code. If someone can share a code for me, i will be glad.


Sign in to comment.

1 Answer

Answer by Greg Heath
on 25 Feb 2019
Edited by Greg Heath
on 25 Feb 2019

0. The genetic approach is a waste of time. It takes too long.
1.Typically, a single hidden layer is sufficient.
2. Minimize the number of hidden nodes by trial and error using a double loop:
a. Outer loop over No. of hidden nodes
b. Inner loop over No. of random initial weight values
3. If you must use genetic, search BOTH the NEWSGROUP and ANSWERS using
greg genetic neural
Hope this helps.

  1 Comment

Thank you for you reply. But, i don't know where i searched 'BOTH the NEWSGROUP and ANSWERS using greg genetic neural'. But, i couldn't find. Can you show me the code. Also, i must use genetic algorithm. My task is to implement genetic algorithm on neural network for the purpose of finding number of hidden layers and neurons. I need a code which i can use for my task.

Sign in to comment.