Bounded activation functions for enhanced training stability of deep neural networks on visual pattern recognition problems

Published 2016 View Full Article

  1. Home
  2. Publications
  3. Publication Search
  4. Publication Details
Title
Bounded activation functions for enhanced training stability of deep neural networks on visual pattern recognition problems
Authors
Keywords
Activation function, Output boundary, Generalization performance, Training stability, Deep neural network, Convolutional neural network
Journal
NEUROCOMPUTING
Volume 216, Issue -, Pages 718-734
Publisher
Elsevier BV
Online
2016-08-15
DOI
10.1016/j.neucom.2016.08.037

Ask authors/readers for more resources

Protocol

Community support

Reagent

Community support

Reprint

Contact the author

Discover Peeref hubs

Discuss science. Find collaborators. Network.

Join a conversation

Ask a Question. Answer a Question.

Quickly pose questions to the entire community. Debate answers and get clarity on the most important issues facing researchers.

Get Started
Webinars Posters Questions Hubs Funding Journals Articles Connect Collections Reviewers About Us FAQs Mobile App Privacy Policy Terms of Use
© Peeref 2019-2024. All rights reserved.