I'm pretty sure this question has already studied by at least one paper, but I can't figure out where. The question is the following :

Given $l$ layers of $n_l \in L$ neurons, we can build a set of functions $\mathcal{N}(l, \{n_i | 1 \leq i \leq l\}\}$, which are the functions given by any neural feedforward neural network with this amount of layers and neuron (n_1 and n_l are respectively the input layers and output layers).

Those functions are continuous $\mathcal{N}(l, n_i) \subset \mathcal{C}(R^n_1, R^n_l)$, and as the number of layers, or the number of neurons in a layer increase, we have bigger set of functions ($\mathcal{N}(l, n_i) \subset \mathcal{N}(l', m_i), \forall l \leq l', n_i \leq m_i$).

But what kind of functions those $\mathcal{N}(l, n_i)$ (let's say n_0 and n_l are given and fixed) sets are approximating? I would be surprised if this set is dense in the set of continuous functions. I guess it is not the case, and then ask what is the smallest human-named set containing those functions. Are they dense in that set? If no, which functions are missing?

Once we know that, what probability law does a uniform law on the weights ''induce'' on this function set?

N.b. : This question is related to computer science, but since I'm looking for functional space, and probabilities, I thought it's better to ask on math exchange.

Edit : Just noticed I'm talking about density but didn't said which topology I'm using. Let's say we are interested to this answer for both $L^2$ and infinite norms.


Your intuition is right on the money. It has been proven that FFNN can approximate any continuous function over a compact subset of $R^n$.


  • $\begingroup$ Thanks a lot, it's a result good to know when you are speaking about FFNN :-D $\endgroup$ – Jeremy Cochoy Dec 15 '15 at 16:04
  • $\begingroup$ As far as I understand from Hornick's result, they can approximate any integrable function – this is a larger space than continuous functions: doi.org/10.1016/0893-6080(91)90009-T $\endgroup$ – pglpm Aug 10 '18 at 14:10

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.