Universal Approximation Theorem

有限個のユニットを持つ一層の隠れ層で構成されるfeed-forward networkは、いくつかの条件のもと、任意の連続関数を近似することが出来る

The key point in the Universal Approximation Theorem is that instead of creating complex mathematical relationships between the input and output, it uses simple linear manipulations to divvy up the complicated function into many small, less complicated pieces, each of which are taken by one neuron.