LGJan 4, 2022
An unfeasability view of neural network learningJoos Heintz, Hvara Ocar, Luis Miguel Pardo et al.
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.