DropCircuit : A Modular Regularizer for Parallel Circuit Networks

DropCircuit : A Modular Regularizer for Parallel Circuit Networks How to design and train increasingly large neural network models is a topic that has been actively researched for several years. However, while there exists a large number of studies on training deeper and/or wider models, there is relatively little systematic research particularly on the effective usage of wide modular neural networks. Addressing this gap, and in an attempt to solve the problem of lengthy training times, we proposed Parallel Circuits (PCs), a biologically inspired architecture based on the design of the retina. In previous work we showed that this approach fails to maintain generalization performance in spite of achieving sharp speed gains. To address this issue, and motivated by the way dropout prevents node co-adaptation, in this paper, we suggest an improvement by extending dropout to the parallel-circuit architecture. The paper provides empirical proof and multiple insights into this combination. Experiments show promising results in which improved error rates are achieved in most cases, whilst maintaining the speed advantage of the PC approach. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Neural Processing Letters Springer Journals

DropCircuit : A Modular Regularizer for Parallel Circuit Networks

Loading next page...
 
/lp/springer_journal/dropcircuit-a-modular-regularizer-for-parallel-circuit-networks-dj4Wj8Il0p
Publisher
Springer Journals
Copyright
Copyright © 2017 by Springer Science+Business Media, LLC
Subject
Computer Science; Artificial Intelligence (incl. Robotics); Complex Systems; Computational Intelligence
ISSN
1370-4621
eISSN
1573-773X
D.O.I.
10.1007/s11063-017-9677-4
Publisher site
See Article on Publisher Site

Abstract

How to design and train increasingly large neural network models is a topic that has been actively researched for several years. However, while there exists a large number of studies on training deeper and/or wider models, there is relatively little systematic research particularly on the effective usage of wide modular neural networks. Addressing this gap, and in an attempt to solve the problem of lengthy training times, we proposed Parallel Circuits (PCs), a biologically inspired architecture based on the design of the retina. In previous work we showed that this approach fails to maintain generalization performance in spite of achieving sharp speed gains. To address this issue, and motivated by the way dropout prevents node co-adaptation, in this paper, we suggest an improvement by extending dropout to the parallel-circuit architecture. The paper provides empirical proof and multiple insights into this combination. Experiments show promising results in which improved error rates are achieved in most cases, whilst maintaining the speed advantage of the PC approach.

Journal

Neural Processing LettersSpringer Journals

Published: Jul 22, 2017

References

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off