NDLI: The need for small learning rates on large problems

Content Provider	IEEE Xplore Digital Library
Author	Wilson, D.R. Martinez, T.R.
Copyright Year	2001
Description	Author affiliation: fonix Corp., Draper, UT, USA (Wilson, D.R.)
Abstract	In gradient descent learning algorithms such as error backpropagation, the learning rate parameter can have a significant effect on generalization accuracy. In particular, decreasing the learning rate below that which yields the fastest convergence can significantly improve generalization accuracy, especially on large, complex problems. The learning rate also directly affects training speed, but not necessarily in the way that many people expect. Many neural network practitioners currently attempt to use the largest learning rate that still allows for convergence, in order to improve training speed. However, a learning rate that is too large can be as slow as a learning rate that is too small, and a learning rate that is too large or too small can require orders of magnitude more training time than one that is in an appropriate range. The paper illustrates how the learning rate affects training speed and generalization accuracy, and thus gives guidelines on how to efficiently select a learning rate that maximizes generalization accuracy.
Sponsorship	Int. Neural Network Soc.
Starting Page	115
Ending Page	119
File Size	442259
Page Count	5
File Format	PDF
ISBN	0780370449
ISSN	10987576
DOI	10.1109/IJCNN.2001.939002
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2001-07-15
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Convergence Neural networks Computer science Nominations and elections Computer errors Guidelines Approximation algorithms
Content Type	Text
Resource Type	Article

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

Bias and the probability of generalization

Learning algorithms for feedforward networks based on finite samples

Rates of convergence for adaptive regression estimates with multiple hidden layer feedforward neural networks

On stochastic approximation algorithms for classes of PAC learning problems

On MISE convergence rates of radial basis functions networks

Solving flat-spot problem in back-propagation learning algorithm based on magnified error

Generalization enhancement of feedforward neural networks based on the convergence of shape errors

Self-adaptive learning rates in backpropagation algorithm improve its function approximation performance

Iterative Projection Approximation Algorithms for PCA

The need for small learning rates on large problems

Similar Documents

Bias and the probability of generalization

Learning algorithms for feedforward networks based on finite samples

Rates of convergence for adaptive regression estimates with multiple hidden layer feedforward neural networks

On stochastic approximation algorithms for classes of PAC learning problems

On MISE convergence rates of radial basis functions networks

Solving flat-spot problem in back-propagation learning algorithm based on magnified error

Generalization enhancement of feedforward neural networks based on the convergence of shape errors

Self-adaptive learning rates in backpropagation algorithm improve its function approximation performance

Iterative Projection Approximation Algorithms for PCA

The need for small learning rates on large problems