training neural network using genetic algorithm

Question

I have an optimisation problem where the objective function I want to maximise is not differentiable. I've trained a linear model using genetic algorithm, but the performance the linear model is not that good. I am thinking about replacing the linear model with a neural network. But my understanding is that with a non-differentiable objective function I cannot use the backprop method to do updates. So, does anyone know how to use the genetic algorithm to train a neural network?

Thomas Wagenaar · Accepted Answer · 2017-05-25 11:00:38Z

1

Yes. This is called neuro-evolution. If you are good at programming, you could make your own NEAT (neuroevolution of augmenting topologies) implementation. However, there are already a lot of implementations out there.

If you want to play around with neuroevolution first, you might want to check out Neataptic. All you need to do is set up the network and run a single function to get the neuroevolution started.

answered May 25, 2017 at 11:00

Thomas Wagenaar

6,8496 gold badges36 silver badges84 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

ascetic652 Over a year ago

Can you suggest any implementations or examples I should look at?@Thomas W

Thomas Wagenaar Over a year ago

@ascetic652 well here for example Neataptic is used to evolve genomes to play agario

Collectives™ on Stack Overflow

training neural network using genetic algorithm

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related