Concentration Inequalities and Optimal Number of Layers for Stochastic Deep Neural Networks

Concentration Inequalities and Optimal Number of Layers for Stochastic Deep Neural Networks

We state concentration 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...

Full description

Bibliographic Details
Main Authors: Michele Caprio, Sayan Mukherjee
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Stochastic deep neural network
feedforward neural network
ReLU activation
concentration inequality
martingales
optimal stopping
Online Access:https://ieeexplore.ieee.org/document/10103873/

Internet

https://ieeexplore.ieee.org/document/10103873/

Similar Items