Concentration inequalities and optimal number of layers for stochastic deep neural networks. (arXiv:2206.11241v1 [cs.LG])

Web: http://arxiv.org/abs/2206.11241

We state concentration and martingale inequalities for the output of the
hidden layers of a stochastic deep neural network (SDNN), as well as for the
output of the whole SDNN. These results allow us to introduce an expected
classifier (EC), and to give probabilistic upper bound for the classification
error of the EC. We also state the optimal number of layers for the SDNN via an
optimal stopping procedure. We apply our analysis to a stochastic version of a
feedforward …

arxiv deep lg networks neural neural networks stochastic