4
$\begingroup$

Across my studies I have noticed the following statement in my Subject Guide; namely, that two-layer feed-forward neural networks using the sigmoidal activation function are universal. My question is how are the networks 'universal' and what does 'universal' actually mean in this instance?

Thanks in advance.

$\endgroup$

1 Answer 1

4
$\begingroup$

I think they are talking about the universal approximation theorem which states that given a continuous function $f$ over an n-dimensional input vector $\vec{x}$, then a neural network with a single hidden layer can approximate $f(\vec{x})$ arbitrarily closely.

$\endgroup$
2
  • $\begingroup$ Thanks, that point really helped. Are there any other references that discuss the universal approximation theorem? $\endgroup$ Apr 26, 2013 at 20:53
  • 1
    $\begingroup$ LMGTFY bit.ly/ZB0HBY $\endgroup$ Apr 26, 2013 at 21:45

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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