WebSite Logo
  • Content
  • Similar Resources
  • Metadata
  • Cite This
  • Log-in
  • Fullscreen
Log-in
Do not have an account? Register Now
Forgot your password? Account recovery
  1. Science in China Series : Information Sciences
  2. Science in China Series : Information Sciences : Volume 59
  3. Science in China Series : Information Sciences : Volume 59, Issue 7, July 2016
  4. Dropout Rademacher complexity of deep neural networks
Loading...

Please wait, while we are loading the content...

Science in China Series : Information Sciences : Volume 61
Science in China Series : Information Sciences : Volume 60
Science in China Series : Information Sciences : Volume 59
Science in China Series : Information Sciences : Volume 59, Issue 12, December 2016
Science in China Series : Information Sciences : Volume 59, Issue 11, November 2016
Science in China Series : Information Sciences : Volume 59, Issue 10, October 2016
Science in China Series : Information Sciences : Volume 59, Issue 9, September 2016
Science in China Series : Information Sciences : Volume 59, Issue 8, August 2016
Science in China Series : Information Sciences : Volume 59, Issue 7, July 2016
New constructions of q-variable 1-resilient rotation symmetric functions over $\mathbb{F}_p $
Sketch-based stroke generation in Chinese flower painting
Further results on cloud control systems
Identification of the clustering structure in microbiome data by density clustering on the Manhattan distance
GOAL: the comprehensive gene ontology analysis layer
Integrating phenotypic features and tissue-specific information to prioritize disease genes
Understanding tissue-specificity with human tissue-specific regulatory networks
Identifying essential proteins based on dynamic protein-protein interaction networks and RNA-Seq datasets
Dropout Rademacher complexity of deep neural networks
Further results on quantized stabilization of nonlinear cascaded systems with dynamic uncertainties
A method for automatically translating print books into electronic Braille books
Pinning controllability of autonomous Boolean control networks
Detecting protein complexes from DPINs by density based clustering with Pigeon-Inspired Optimization Algorithm
Identifying disease modules and components of viral infections based on multi-layer networks
High-level representation sketch for video event retrieval
Efficient compressive sensing tracking via mixed classifier decision
The Sunway TaihuLight supercomputer: system and applications
A large-scale flight multi-objective assignment approach based on multi-island parallel evolution algorithm with cooperative coevolutionary
Minimum sliding mode error feedback control for inner-formation satellite system with J $_{2}$ and small eccentricity
High-confidence software evolution
Science in China Series : Information Sciences : Volume 59, Issue 6, June 2016
Science in China Series : Information Sciences : Volume 59, Issue 5, May 2016
Science in China Series : Information Sciences : Volume 59, Issue 4, April 2016
Science in China Series : Information Sciences : Volume 59, Issue 2, February 2016
Science in China Series : Information Sciences : Volume 59, Issue 1, January 2016
Science in China Series : Information Sciences : Volume 58
Science in China Series : Information Sciences : Volume 57
Science in China Series : Information Sciences : Volume 56
Science in China Series : Information Sciences : Volume 55
Science in China Series : Information Sciences : Volume 54
Science in China Series : Information Sciences : Volume 53
Science in China Series : Information Sciences : Volume 52
Science in China Series : Information Sciences : Volume 51
Science in China Series : Information Sciences : Volume 50
Science in China Series : Information Sciences : Volume 49
Science in China Series : Information Sciences : Volume 48
Science in China Series : Information Sciences : Volume 47
Science in China Series : Information Sciences : Volume 46
Science in China Series : Information Sciences : Volume 45
Science in China Series : Information Sciences : Volume 44

Similar Documents

...
Dropout Rademacher Complexity of Deep Neural Networks

Article

...
Dropout Rademacher Complexity Of Deep Neural Networks

...
Adversarial Rademacher Complexity of Deep Neural Networks

Article

...
4 Dropout Rademacher Complexity of Deep Neural Networks

...
A Deep Connection Between the Vapnik–Chervonenkis Entropy and the Rademacher Complexity

Article

...
Intelligent data structures selection using neural networks

Article

...
A general framework for scalable transductive transfer learning

Article

...
Dither is Better than Dropout for Regularising Deep Neural Networks

Article

...
Survey of Dropout Methods for Deep Neural Networks

Article

Dropout Rademacher complexity of deep neural networks

Content Provider Springer Nature Link
Author Gao, Wei Zhou, Zhi Hua
Copyright Year 2016
Abstract Great successes of deep neural networks have been witnessed in various real applications. Many algorithmic and implementation techniques have been developed; however, theoretical understanding of many aspects of deep neural networks is far from clear. A particular interesting issue is the usefulness of dropout, which was motivated from the intuition of preventing complex co-adaptation of feature detectors. In this paper, we study the Rademacher complexity of different types of dropouts, and our theoretical results disclose that for shallow neural networks (with one or none hidden layer) dropout is able to reduce the Rademacher complexity in polynomial, whereas for deep neural networks it can amazingly lead to an exponential reduction.
Starting Page 1
Ending Page 12
Page Count 12
File Format PDF
ISSN 1674733X
Journal Science in China Series : Information Sciences
Volume Number 59
Issue Number 7
e-ISSN 18691919
Language English
Publisher Science China Press
Publisher Date 2016-06-16
Publisher Place Beijing
Access Restriction One Nation One Subscription (ONOS)
Subject Keyword artificial intelligence machine learning deep learning dropout Rademacher complexity Information Systems and Communication Service
Content Type Text
Resource Type Article
Subject Computer Science
  • About
  • Disclaimer
  • Feedback
  • Sponsor
  • Contact
  • Chat with Us
About National Digital Library of India (NDLI)
NDLI logo

National Digital Library of India (NDLI) is a virtual repository of learning resources which is not just a repository with search/browse facilities but provides a host of services for the learner community. It is sponsored and mentored by Ministry of Education, Government of India, through its National Mission on Education through Information and Communication Technology (NMEICT). Filtered and federated searching is employed to facilitate focused searching so that learners can find the right resource with least effort and in minimum time. NDLI provides user group-specific services such as Examination Preparatory for School and College students and job aspirants. Services for Researchers and general learners are also provided. NDLI is designed to hold content of any language and provides interface support for 10 most widely used Indian languages. It is built to provide support for all academic levels including researchers and life-long learners, all disciplines, all popular forms of access devices and differently-abled learners. It is designed to enable people to learn and prepare from best practices from all over the world and to facilitate researchers to perform inter-linked exploration from multiple sources. It is developed, operated and maintained from Indian Institute of Technology Kharagpur.

Learn more about this project from here.

Disclaimer

NDLI is a conglomeration of freely available or institutionally contributed or donated or publisher managed contents. Almost all these contents are hosted and accessed from respective sources. The responsibility for authenticity, relevance, completeness, accuracy, reliability and suitability of these contents rests with the respective organization and NDLI has no responsibility or liability for these. Every effort is made to keep the NDLI portal up and running smoothly unless there are some unavoidable technical issues.

Feedback

Sponsor

Ministry of Education, through its National Mission on Education through Information and Communication Technology (NMEICT), has sponsored and funded the National Digital Library of India (NDLI) project.

Contact National Digital Library of India
Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302
See location in the Map
03222 282435
Mail: support@ndl.gov.in
Sl. Authority Responsibilities Communication Details
1 Ministry of Education (GoI),
Department of Higher Education
Sanctioning Authority https://www.education.gov.in/ict-initiatives
2 Indian Institute of Technology Kharagpur Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project https://www.iitkgp.ac.in
3 National Digital Library of India Office, Indian Institute of Technology Kharagpur The administrative and infrastructural headquarters of the project Dr. B. Sutradhar  bsutra@ndl.gov.in
4 Project PI / Joint PI Principal Investigator and Joint Principal Investigators of the project Dr. B. Sutradhar  bsutra@ndl.gov.in
Prof. Saswat Chakrabarti  will be added soon
5 Website/Portal (Helpdesk) Queries regarding NDLI and its services support@ndl.gov.in
6 Contents and Copyright Issues Queries related to content curation and copyright issues content@ndl.gov.in
7 National Digital Library of India Club (NDLI Club) Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach clubsupport@ndl.gov.in
8 Digital Preservation Centre (DPC) Assistance with digitizing and archiving copyright-free printed books dpc@ndl.gov.in
9 IDR Setup or Support Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops idr@ndl.gov.in
I will try my best to help you...
Cite this Content
Loading...