Deep Learning of Nonnegativity-Constrained Autoencoders for Enhanced Understanding of Data

Unsupervised feature extractors are known to perform an efficient and discriminative representation of data. Insight into the mappings they perform and human ability to understand them, however, remain very limited. This is especially prominent when multilayer deep learning architectures are used. T...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:arXiv.org
Hlavní autoři: Ayinde, Babajide O, Zurada, Jacek M
Médium: Paper
Jazyk:angličtina
Vydáno: Ithaca Cornell University Library, arXiv.org 25.12.2018
Témata:
ISSN:2331-8422
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Unsupervised feature extractors are known to perform an efficient and discriminative representation of data. Insight into the mappings they perform and human ability to understand them, however, remain very limited. This is especially prominent when multilayer deep learning architectures are used. This paper demonstrates how to remove these bottlenecks within the architecture of Nonnegativity Constrained Autoencoder (NCSAE). It is shown that by using both L1 and L2 regularization that induce nonnegativity of weights, most of the weights in the network become constrained to be nonnegative thereby resulting into a more understandable structure with minute deterioration in classification accuracy. Also, this proposed approach extracts features that are more sparse and produces additional output layer sparsification. The method is analyzed for accuracy and feature interpretation on the MNIST data, the NORB normalized uniform object data, and the Reuters text categorization dataset.
AbstractList Unsupervised feature extractors are known to perform an efficient and discriminative representation of data. Insight into the mappings they perform and human ability to understand them, however, remain very limited. This is especially prominent when multilayer deep learning architectures are used. This paper demonstrates how to remove these bottlenecks within the architecture of Nonnegativity Constrained Autoencoder (NCSAE). It is shown that by using both L1 and L2 regularization that induce nonnegativity of weights, most of the weights in the network become constrained to be nonnegative thereby resulting into a more understandable structure with minute deterioration in classification accuracy. Also, this proposed approach extracts features that are more sparse and produces additional output layer sparsification. The method is analyzed for accuracy and feature interpretation on the MNIST data, the NORB normalized uniform object data, and the Reuters text categorization dataset.
Author Zurada, Jacek M
Ayinde, Babajide O
Author_xml – sequence: 1
  givenname: Babajide
  surname: Ayinde
  middlename: O
  fullname: Ayinde, Babajide O
– sequence: 2
  givenname: Jacek
  surname: Zurada
  middlename: M
  fullname: Zurada, Jacek M
BookMark eNotTsFOwzAUixBIjLEP4FaJc0eS1zTpcdrGQKrgMi5cpjR9GZ3Qy0jTCf6eIuaLJduyfcMuKRAydif4vDBK8Qcbv7vTXBgu53wEXLCJBBC5KaS8ZrO-P4yqLLVUCibsfYV4zGq0kTraZ8FnL4EI9zZ1py795MtAfYq2I2yzxZACkgstxj7zIWZr-rDkRueN_rRkqT2XrGyyt-zK288eZ2eesu3jert8yuvXzfNyUedWySq3TcVboT1oVxYNFKYplGkRwZvGCyVhDIz_eQOl0rp12jUctROVRa_RaZiy-__aYwxfA_ZpdwhDpHFxJ7kWIDiYCn4B-aVWmg
ContentType Paper
Copyright 2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID 8FE
8FG
ABJCF
ABUWG
AFKRA
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
HCIFZ
L6V
M7S
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
DOI 10.48550/arxiv.1802.00003
DatabaseName ProQuest SciTech Collection
ProQuest Technology Collection
Materials Science & Engineering Collection
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
ProQuest Central Essentials
ProQuest Central
ProQuest Technology Collection
ProQuest One
ProQuest Central Korea
SciTech Premium Collection
ProQuest Engineering Collection
Engineering Database
ProQuest Central Premium
ProQuest One Academic (New)
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
Engineering Collection
DatabaseTitle Publicly Available Content Database
Engineering Database
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Central Essentials
ProQuest One Academic Eastern Edition
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Technology Collection
ProQuest SciTech Collection
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Engineering Collection
ProQuest One Academic UKI Edition
ProQuest Central Korea
Materials Science & Engineering Collection
ProQuest Central (New)
ProQuest One Academic
ProQuest One Academic (New)
Engineering Collection
DatabaseTitleList Publicly Available Content Database
Database_xml – sequence: 1
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Physics
EISSN 2331-8422
Genre Working Paper/Pre-Print
GroupedDBID 8FE
8FG
ABJCF
ABUWG
AFKRA
ALMA_UNASSIGNED_HOLDINGS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
FRJ
HCIFZ
L6V
M7S
M~E
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
ID FETCH-LOGICAL-a529-ab90d17f37c64b348b458dee3f8bf1523ab92330b36577dc7cb0e7c19aef7ec73
IEDL.DBID M7S
IngestDate Mon Jun 30 09:39:18 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a529-ab90d17f37c64b348b458dee3f8bf1523ab92330b36577dc7cb0e7c19aef7ec73
Notes SourceType-Working Papers-1
ObjectType-Working Paper/Pre-Print-1
content type line 50
OpenAccessLink https://www.proquest.com/docview/2071310389?pq-origsite=%requestingapplication%
PQID 2071310389
PQPubID 2050157
ParticipantIDs proquest_journals_2071310389
PublicationCentury 2000
PublicationDate 20181225
PublicationDateYYYYMMDD 2018-12-25
PublicationDate_xml – month: 12
  year: 2018
  text: 20181225
  day: 25
PublicationDecade 2010
PublicationPlace Ithaca
PublicationPlace_xml – name: Ithaca
PublicationTitle arXiv.org
PublicationYear 2018
Publisher Cornell University Library, arXiv.org
Publisher_xml – name: Cornell University Library, arXiv.org
SSID ssj0002672553
Score 1.6748518
SecondaryResourceType preprint
Snippet Unsupervised feature extractors are known to perform an efficient and discriminative representation of data. Insight into the mappings they perform and human...
SourceID proquest
SourceType Aggregation Database
SubjectTerms Deep learning
Feature extraction
Human performance
Multilayers
Regularization
Title Deep Learning of Nonnegativity-Constrained Autoencoders for Enhanced Understanding of Data
URI https://www.proquest.com/docview/2071310389
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3PT8MgGCW6aeLJ3_HHXDh4RdvSFjgZdVv0YNPoTKaXBShsu7Sz7Rb_fAE7NTHx4pFACIH0-x4fr-8BcO5pg2mlJ1GIwwyFXGMkJOFIxzwWmBArAubMJkiS0NGIpU3BrWpolauY6AJ1VkhbI7eVEN96YlF2NX9D1jXKvq42FhrroG1VEnxH3Xv6qrEEMTGIGX8-Zjrprktevs-WF1b2zCkX4l8h2OWVwfZ_V7QD2imfq3IXrKl8D2w6Pqes9sFrT6k5bMRTJ7DQMLGMlkljFoGsT6dzh1AZvF7UhZWztJRmaDAs7OdTxwuAzz__fLGT9HjND8Bw0B_e3qHGRgHxKGCIC-ZlPtGYyDgUOKQijGimFNZUaJO9sRkQYOwJHEeEZJJI4SkifcaVJkoSfAhaeZGrIwC1SfcyZNSJ-pibnFDEwEfJmJlRUU8cg85qp8bNp1CNv7fp5O_uU7Bl0Ai1XJEg6oBWXS7UGdiQy3pWlV3Qvukn6WPXnbBppfcP6csHOLmxjg
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3LTgIxFL1B0OjKd3ygdqHL6jCdmU4XxhiBQEBCIibEDWk7LbIB5KV-lP9oWxg1MXHHwvVMmszc9vbc29NzAM49bTCt9CQOSJDggGuChaQc64hHglBqRcCc2QRtNOJ2mzUz8JHehbG0yjQnukSdDKTtkdtOSMF6YsXsZviCrWuUPV1NLTTm06Km3l9NyTa-rhZNfC98v1xq3VXwwlUA89BnmAvmJQWqCZVRIEgQiyCME6WIjoU2mxkxL_imyBckCilNJJXCU1QWGFeaKkmJGXYFcgZF-MwxBR--Wjp-RA1AJ_OzU6cUdsVHb73ZpVVZc0KJ5FfGd9tYefOf_YAtyDX5UI22IaP6O7Dm2KpyvAtPRaWGaCEN20UDjRqWr9NdWGFg60LqvC9Ugm6nk4EV67SEbWQQOir1nx3rAT3-vNdjBynyCd-D1jK-Zh-y_UFfHQDSBszIgMVOssjUqUJRA44lY2ZEFXviEPJpYDqLhT7ufEfl6O_HZ7Bead3XO_Vqo3YMGwZ3xZYV44d5yE5GU3UCq3I26Y1Hp25SIegsOYafo1ILXQ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Deep+Learning+of+Nonnegativity-Constrained+Autoencoders+for+Enhanced+Understanding+of+Data&rft.jtitle=arXiv.org&rft.au=Ayinde%2C+Babajide+O&rft.au=Zurada%2C+Jacek+M&rft.date=2018-12-25&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422&rft_id=info:doi/10.48550%2Farxiv.1802.00003