Which Neural Net Architectures Give Rise To Exploding and Vanishing Gradients?

MaRDI QIDQ7102020arXivFDO

Authors Boris Hanin

Publication date 2018

Published in arXiv

arXiv classification

stat.ML

Cited in

(1)

• High Probability Derivative Bounds for Random tanh Neural Networks on a Hypercube

This page was built for publication: Which Neural Net Architectures Give Rise To Exploding and Vanishing Gradients?

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7102020)