NDLI: Mean-normalized stochastic gradient for large-scale deep learning

Content Provider	IEEE Xplore Digital Library
Author	Wiesler, S. Richard, A. Schluter, R. Ney, H.
Copyright Year	2014
Description	Author affiliation: Comput. Sci. Dept., RWTH Aachen Univ., Aachen, Germany (Wiesler, S.; Richard, A.; Schluter, R.; Ney, H.)
Abstract	Deep neural networks are typically optimized with stochastic gradient descent (SGD). In this work, we propose a novel second-order stochastic optimization algorithm. The algorithm is based on analytic results showing that a non-zero mean of features is harmful for the optimization. We prove convergence of our algorithm in a convex setting. In our experiments we show that our proposed algorithm converges faster than SGD. Further, in contrast to earlier work, our algorithm allows for training models with a factorized structure from scratch. We found this structure to be very useful not only because it accelerates training and decoding, but also because it is a very effective means against overfitting. Combining our proposed optimization algorithm with this model structure, model size can be reduced by a factor of eight and still improvements in recognition error rate are obtained. Additional gains are obtained by improving the Newbob learning rate strategy.
Sponsorship	IEEE Signal Process. Soc.
Starting Page	180
Ending Page	184
File Size	111314
Page Count	5
File Format	PDF
ISBN	9781479928934
DOI	10.1109/ICASSP.2014.6853582
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2014-05-04
Publisher Place	Italy
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Training Neural networks Optimization Stochastic processes Error analysis Speech recognition Speech LVCSR deep learning optimization speech recognition
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

Exploring one pass learning for deep neural network training with averaged stochastic gradient descent

Investigation of stochastic Hessian-Free optimization in Deep neural networks for speech recognition

Improving training time of deep neural networkwith asynchronous averaged stochastic gradient descent

MEAN-NORMALIZED STOCHASTIC GRADIENT FOR LARGE-SCALE DEEP LEARNING

An empirical study of learning rates in deep neural networks for speech recognition

Improvements to Deep Convolutional Neural Networks for LVCSR

Improving deep neural networks for LVCSR using rectified linear units and dropout

Deep convolutional neural networks for LVCSR

Stochastic pooling maxout networks for low-resource speech recognition

Mean-normalized stochastic gradient for large-scale deep learning

Similar Documents

Exploring one pass learning for deep neural network training with averaged stochastic gradient descent

Investigation of stochastic Hessian-Free optimization in Deep neural networks for speech recognition

Improving training time of deep neural networkwith asynchronous averaged stochastic gradient descent

MEAN-NORMALIZED STOCHASTIC GRADIENT FOR LARGE-SCALE DEEP LEARNING

An empirical study of learning rates in deep neural networks for speech recognition

Improvements to Deep Convolutional Neural Networks for LVCSR

Improving deep neural networks for LVCSR using rectified linear units and dropout

Deep convolutional neural networks for LVCSR

Stochastic pooling maxout networks for low-resource speech recognition

Mean-normalized stochastic gradient for large-scale deep learning