Sign in to follow this  
  • entries
    42
  • comments
    61
  • views
    32840

Assisted learning?

Sign in to follow this  

259 views

So I've had little luck with training my neural network. I believe the problem is in the implementation. I put together a quick-n-dirty genetic algorith to train the network where the best network from each generation is used to spawn the next generation. To avoid suboptimal, local minima I should keep a selection of individuals from each generation, hopefully individuals that encode different strategies. Then, hopefully, progress for the population will not be retarded by one individual staying in a local minimum.

So I will probably implements this approach but I also thought of another approach that I'd like to try.

The solution that the neural network is learning is not what I would choose. So I wonder if it would be possible to solve the pursuit problem myself a few times and record the responses that I use. Then train the neural network to learn how I solved the problem. After learning my approach, I would let the neural network try to find a better solution to the original problem by itself. I hope that this kind of "assisted learning" would be a useful way of getting the learning on the right track from the start.

I am sure this is not the first time someone has used this approach. I've called it "assisted learning" but I'm sure it is called something else in the literature. Does anyone know any references to this kind of work?


-Josh



Sign in to follow this  


0 Comments


Recommended Comments

There are no comments to display.

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now