1
$\begingroup$

I have heard that only a single layer is needed for an artificial neural network to fit any possible function (input to output).

  1. Is this true and where is this shown?

  2. If this is true, then what is the advantage of having multiple layers?

$\endgroup$

1 Answer 1

1
$\begingroup$

Search for the subject: How many hidden layers should I use?

http://www.faqs.org/faqs/ai-faq/neural-nets/part3/

$\endgroup$
3
  • $\begingroup$ the material on the site is not written to modern standard IMHO. I would hope that someone who is aquainted with the subject would give a nice answer here for others to then use; as an improvement. Or supply the names of some good papers that they believe is a first source for this question. $\endgroup$
    – Vass
    May 23, 2011 at 14:21
  • 1
    $\begingroup$ @Vass - you may want to ask this over at metaoptimize.com/qa if you are still looking for a more rigorous answer. $\endgroup$
    – GEL
    Jun 17, 2011 at 21:32
  • $\begingroup$ amazing link!!! Thank you. How come I never heard of this site?? I love it, because it is theoretical and practical. $\endgroup$
    – Vass
    Jun 25, 2011 at 13:44

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .