Related Experiment Video
Updated: Aug 8, 2026

Controlled Synthesis and Fluorescence Tracking of Highly Uniform Poly(N-isopropylacrylamide) Microgels
Published on: September 8, 2016
Kolmogorov's Theorem Is Relevant
1Institute of Computer Science, Czechoslovak Academy of Sciences, P. O. Box 5, 182 07 Prague 8, Czechoslovakia.
Abstract:
We show that Kolmogorov's theorem on representations of continuous functions of n-variables by sums and superpositions of continuous functions of one variable is relevant in the context of neural networks. We give a version of this theorem with all of the one-variable functions approximated arbitrarily well by linear combinations of compositions of affine functions with some given sigmoidal function. We derive an upper estimate of the number of hidden units.
More Related Videos
Related Concept Videos
Chebyshev's Theorem to Interpret Standard Deviation
Theorems of Pappus and Guldinus
For finding the surface area, consider a differential line element that generates a ring with surface area dA when revolved.
Parseval's Theorem
Interestingly, Parseval's theorem also holds for the trigonometric form of the Fourier series, which expresses a...
Fundamental Theorem of Algebra
Green’s Theorem
Extended Versions of Green’s Theorem

