Substantiation of the backpropagation technique via the Hamilton—Pontryagin formalism for training nonconvex nonsmooth neural networks

The paper observes the similarity between the stochastic optimal control over discrete dynamical systems and the lear ning multilayer neural networks. It focuses on contemporary deep networks with nonconvex nonsmooth loss and activation functions. The machine learning problems are treated as nonco...

Full description

Saved in:
Bibliographic Details
Published in:Доповіді НАН України
Date:2019
Main Author: Norkin, V.I.
Format: Article
Language:English
Published: Видавничий дім "Академперіодика" НАН України 2019
Subjects:
Online Access:https://nasplib.isofts.kiev.ua/handle/123456789/162684
Tags: Add Tag
No Tags, Be the first to tag this record!
Journal Title:Digital Library of Periodicals of National Academy of Sciences of Ukraine
Cite this:Substantiation of the backpropagation technique via the Hamilton—Pontryagin formalism for training nonconvex nonsmooth neural networks / V.I. Norkin // Доповіді Національної академії наук України. — 2019. — № 12. — С. 19-26. — Бібліогр.: 15 назв. — англ.

Institution

Digital Library of Periodicals of National Academy of Sciences of Ukraine