You are not logged in.
Openly accessible

Faster training of very deep networks via p-norm gates

Pham, Trang, Tran, Truyen, Phung, Dinh and Venkatesh, Svetha 2016, Faster training of very deep networks via p-norm gates, in ICPR 2016: Proceedings of the 23rd International Conference on Pattern Recognition, IEEE, Piscataway, N.J., pp. 3542-3547, doi: 10.1109/ICPR.2016.7900183.

Attached Files
Name Description MIMEType Size Downloads
pham-fastertraining-post-2016.pdf Accepted version application/pdf 802.94KB 2

Title Faster training of very deep networks via p-norm gates
Author(s) Pham, Trang
Tran, TruyenORCID iD for Tran, Truyen orcid.org/0000-0001-6531-8907
Phung, DinhORCID iD for Phung, Dinh orcid.org/0000-0002-9977-8247
Venkatesh, SvethaORCID iD for Venkatesh, Svetha orcid.org/0000-0001-8675-6631
Conference name Pattern Recognition. International Conference (23rd : 2016 : Cancun, Mexico)
Conference location Cancun, Mexico
Conference dates 4-8 Dec. 2016
Title of proceedings ICPR 2016: Proceedings of the 23rd International Conference on Pattern Recognition
Publication date 2016
Conference series Pattern Recognition International Conference
Start page 3542
End page 3547
Total pages 6
Publisher IEEE
Place of publication Piscataway, N.J.
Summary A major contributing factor to the recent advances in deep neural networks is structural units that let sensory information and gradients to propagate easily. Gating is one such structure that acts as a flow control. Gates are employed in many recent state-of-the-art recurrent models such as LSTM and GRU, and feedforward models such as Residual Nets and Highway Networks. This enables learning in very deep networks with hundred layers and helps achieve record-breaking results in vision (e.g., ImageNet with Residual Nets) and NLP (e.g., machine translation with GRU). However, there is limited work in analysing the role of gating in the learning process. In this paper, we propose a flexible p-norm gating scheme, which allows usercontrollable flow and as a consequence, improve the learning speed. This scheme subsumes other existing gating schemes, including those in GRU, Highway Networks and Residual Nets as special cases. Experiments on large sequence and vector datasets demonstrate that the proposed gating scheme helps improve the learning speed significantly without extra overhead.
ISBN 9781509048472
Language eng
DOI 10.1109/ICPR.2016.7900183
Field of Research 080109 Pattern Recognition and Data Mining
Socio Economic Objective 0 Not Applicable
HERDC Research category E1 Full written paper - refereed
ERA Research output type E Conference publication
Copyright notice ©2016, IEEE
Free to Read? Yes
Persistent URL http://hdl.handle.net/10536/DRO/DU:30096794

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 43 Abstract Views, 6 File Downloads  -  Detailed Statistics
Created: Tue, 30 May 2017, 17:06:28 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.