An unfeasability view of neural network learning

01/04/2022

∙

by   Joos Heintz, et al.

∙

0

∙

share

We define the notion of a continuously differentiable perfect learning algorithm for multilayer neural network architectures and show that such algorithms don't exist provided that the length of the data set exceeds the number of involved parameters and the activation functions are logistic, tanh or sin.