MLP - minami-public

MLP

hidden layerが一つであるMLPは、任意の連続関数を任意の精度で近似できる = 普遍性定理 (Universal Approximation theorem)

The universal approximation theorem means that regardless of what functionwe are trying to learn, we know that a large MLP will be able to represent thisfunction.

In summary, a feedforward network with a single layer is suﬃcient to representany function, but the layer may be infeasibly large and may fail to learn andgeneralize correctly

https://www.deeplearningbook.org/contents/mlp.html

6.4.1 Universal Approximation Properties and Depth

public