9
$\begingroup$

I've read that the most of the problems can be solved with 1-2 hidden layers.

How do you know you need more than 2? For what kind of problems you would need them (give me an example)?

$\endgroup$
  • $\begingroup$ For the sake of consistency should I correct to numbers or to words? I've been correcting to numbers so far. $\endgroup$ – FreezePhoenix Apr 11 '18 at 18:49
  • $\begingroup$ @Pheo What you feel is good, I'm not native so I can't tell the difference much. If I won't be sure, I leave it for the voting. So you can see whether the edit was good or not after the votes. $\endgroup$ – kenorb Apr 11 '18 at 18:52
11
$\begingroup$

Formally, a single hidden layer is sufficient to approximate a continuous function to any desired degree of accuracy, so in that sense, you never need more than 1. This is called the Universal Approximation Theorem.

Finding the best topology for a given problem is an open research problem. As far as I know, there are few universal 'rules of thumb' for this.

For a given problem, one option is to apply a neuroevolutionary approach such as NEAT, which attempts to find a topology that works well for the problem at hand.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.