Dynamic Modification of Activation Function using the Backpropagation Algorithm in the Artificial Neural Networks

The paper proposes the dynamic modification of the activation function in a learning technique, more exactly backpropagation algorithm. The modification consists in changing slope of sigmoid function for activation function according to increase or decrease the error in an epoch of learning. The stu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of advanced computer science & applications Jg. 10; H. 4
Hauptverfasser: Mercioni, Marina Adriana, Tiron, Alexandru, Holban, Stefan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: West Yorkshire Science and Information (SAI) Organization Limited 2019
Schlagworte:
Algorithms
Artificial neural networks
Back propagation
Back propagation networks
Machine learning
Multilayer perceptrons
Neural networks
ISSN:2158-107X, 2156-5570
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract The paper proposes the dynamic modification of the activation function in a learning technique, more exactly backpropagation algorithm. The modification consists in changing slope of sigmoid function for activation function according to increase or decrease the error in an epoch of learning. The study was done using the Waikato Environment for Knowledge Analysis (WEKA) platform to complete adding this feature in Multilayer Perceptron class. This study aims the dynamic modification of activation function has changed to relative gradient error, also neural networks with hidden layers have not used for it.
AbstractList The paper proposes the dynamic modification of the activation function in a learning technique, more exactly backpropagation algorithm. The modification consists in changing slope of sigmoid function for activation function according to increase or decrease the error in an epoch of learning. The study was done using the Waikato Environment for Knowledge Analysis (WEKA) platform to complete adding this feature in Multilayer Perceptron class. This study aims the dynamic modification of activation function has changed to relative gradient error, also neural networks with hidden layers have not used for it.
Author Holban, Stefan
Tiron, Alexandru
Mercioni, Marina Adriana
Author_xml – sequence: 1
  givenname: Marina Adriana
  surname: Mercioni
  fullname: Mercioni, Marina Adriana
– sequence: 2
  givenname: Alexandru
  surname: Tiron
  fullname: Tiron, Alexandru
– sequence: 3
  givenname: Stefan
  surname: Holban
  fullname: Holban, Stefan
BookMark eNp9kMlOwzAQhi0EEqX0DThE4pziNQu3UCgUFTgAEjfLcZ3WXezWdkB9e9KkJw7MZWak_5_luwCnxhoFwBWCQ0RZkt9MnovRezHEEOVDiCCkMDkBPYxYEjOWwtO2zmIE069zMPB-CZsgOU4y0gO7-70RGy2jFzvTlZYiaGsiW0WFDPq768a1kW1Re23mUVio6E7I1dbZrZh3kmI9t06HxSbSphUULhzGabGOXlXt2hR-rFv5S3BWibVXg2Pug8_xw8foKZ6-PU5GxTSWBLMQY0yEQAqXRDBIS1jRlMqyFDATSZWTEikxQ1lFMSMSyZnEqcjo4a9c5lkJMemD625uc-euVj7wpa2daVZynLCEZClGsFHRTiWd9d6pim-d3gi35wjyli_v-PIDX37k29hu_9ikDi2K4IRe_2_-BY9_g44
CitedBy_id crossref_primary_10_1007_s11219_023_09642_4
ContentType Journal Article
Copyright 2019. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: 2019. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID AAYXX
CITATION
3V.
7XB
8FE
8FG
8FK
8G5
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
GNUQQ
GUQSH
HCIFZ
JQ2
K7-
M2O
MBDVC
P5Z
P62
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
Q9U
DOI 10.14569/IJACSA.2019.0100406
DatabaseName CrossRef
ProQuest Central (Corporate)
ProQuest Central (purchase pre-March 2016)
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central (Alumni) (purchase pre-March 2016)
Research Library (Alumni Edition)
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Central
Technology Collection
ProQuest One Community College
ProQuest Central
ProQuest Central Student
Research Library Prep
SciTech Premium Collection
ProQuest Computer Science Collection
Computer Science Database
Research Library
Research Library (Corporate)
ProQuest advanced technologies & aerospace journals
ProQuest Advanced Technologies & Aerospace Collection
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)
One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
ProQuest Central Basic
DatabaseTitle CrossRef
Publicly Available Content Database
Research Library Prep
Computer Science Database
ProQuest Central Student
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
Research Library (Alumni Edition)
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Central Korea
ProQuest Research Library
ProQuest Central (New)
Advanced Technologies & Aerospace Collection
ProQuest Central Basic
ProQuest One Academic Eastern Edition
ProQuest Technology Collection
ProQuest SciTech Collection
Advanced Technologies & Aerospace Database
ProQuest One Academic UKI Edition
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
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 Computer Science
EISSN 2156-5570
ExternalDocumentID 10_14569_IJACSA_2019_0100406
GroupedDBID .DC
5VS
8G5
AAYXX
ABUWG
ADMLS
AFFHD
AFKRA
ALMA_UNASSIGNED_HOLDINGS
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
CITATION
DWQXO
EBS
EJD
GNUQQ
GUQSH
HCIFZ
K7-
KQ8
M2O
OK1
PHGZM
PHGZT
PIMPY
PQGLB
RNS
3V.
7XB
8FE
8FG
8FK
JQ2
MBDVC
P62
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
PUEGO
Q9U
ID FETCH-LOGICAL-c325t-223aa1e2b3a504b0f474cbba08a6f93b1ead18f4253c1cdc27a8400399c98b023
IEDL.DBID BENPR
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000467916400007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2158-107X
IngestDate Sun Sep 07 03:22:51 EDT 2025
Tue Nov 18 22:14:04 EST 2025
Sat Nov 29 06:19:58 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Issue 4
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c325t-223aa1e2b3a504b0f474cbba08a6f93b1ead18f4253c1cdc27a8400399c98b023
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
OpenAccessLink https://www.proquest.com/docview/2656387210?pq-origsite=%requestingapplication%
PQID 2656387210
PQPubID 5444811
ParticipantIDs proquest_journals_2656387210
crossref_primary_10_14569_IJACSA_2019_0100406
crossref_citationtrail_10_14569_IJACSA_2019_0100406
PublicationCentury 2000
PublicationDate 2019-00-00
PublicationDateYYYYMMDD 2019-01-01
PublicationDate_xml – year: 2019
  text: 2019-00-00
PublicationDecade 2010
PublicationPlace West Yorkshire
PublicationPlace_xml – name: West Yorkshire
PublicationTitle International journal of advanced computer science & applications
PublicationYear 2019
Publisher Science and Information (SAI) Organization Limited
Publisher_xml – name: Science and Information (SAI) Organization Limited
SSID ssj0000392683
Score 2.0814867
Snippet The paper proposes the dynamic modification of the activation function in a learning technique, more exactly backpropagation algorithm. The modification...
SourceID proquest
crossref
SourceType Aggregation Database
Enrichment Source
Index Database
SubjectTerms Algorithms
Artificial neural networks
Back propagation
Back propagation networks
Machine learning
Multilayer perceptrons
Neural networks
Title Dynamic Modification of Activation Function using the Backpropagation Algorithm in the Artificial Neural Networks
URI https://www.proquest.com/docview/2656387210
Volume 10
WOSCitedRecordID wos000467916400007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 2156-5570
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000392683
  issn: 2158-107X
  databaseCode: K7-
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest advanced technologies & aerospace journals
  customDbUrl:
  eissn: 2156-5570
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000392683
  issn: 2158-107X
  databaseCode: P5Z
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2156-5570
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000392683
  issn: 2158-107X
  databaseCode: BENPR
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 2156-5570
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000392683
  issn: 2158-107X
  databaseCode: PIMPY
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Research Library (subscription)
  customDbUrl:
  eissn: 2156-5570
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000392683
  issn: 2158-107X
  databaseCode: M2O
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/pqrl
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3JTsMwELXYDlzYEWvlA1dDEjvbCaXQikUtEYtUuES2kxQEtEAL38-M4xS4wIFLEsmTxMqMZ8t4HiF7bg7RTSklC4UfMQFULPJDzorCD8JCy4BLYcAmwm436vXi1CbcRrasstaJRlHnQ4058gMPHA8eQbziHL68MkSNwr-rFkJjmsxipzKQ89lmq5teTrIsDpj_wPTiBNOGfUzDnt0_B45DfHB6lhxdJVjgFe872DsNgY--26ef6tnYnPbif2e7RBast0mTSjyWyVQxWCGLNZIDtQt7lbweV8D0tDPMsXbIsIsOS5roGv6MtsECmgssle9TcBxpU-pHmBjopIokeerDJMb3z_RhYAjwxVWLCopdQMzJlJ2P1shNu3V9dMIsGAPT3PPHDNwIKd3CU1z6jlBOKUKhlZJOJIMy5soFkXSjElQA167OtRdKiB3h-8c6jhR4ButkZjAcFBuERlqU4HaWED0JIUslfdwfq3LFA9-VgbdJeM2CTNtO5QiY8ZRhxIKMyyrGZci4zDJuk7DJXS9Vp44_6Hdq1mV23Y6yL75t_T68TebxYVUyZofMjN_ei10ypz_GD6O3hhXDBpk-DxkcO94FHFP_DkbS0056-wmAAOkJ
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LT9wwEB6hpVK5FNpS8a4P9GhIYud1QCg8Viywq5UK0nJKbSehKyAL7ALiT_EbmXESaC_tiQOnRMokke0v83Bm5gNYdzOMbgqleCj9iEuU4pEfCp7nfhDmRgVCSUs2EfZ60WAQ96fgqamFobTKRidaRZ2NDO2Rb3roeIgI4xVn-_qGE2sU_V1tKDQqWBzljw8Yso23Onu4vj88r71_snvAa1YBboTnTzjaQ6Xc3NNC-Y7UTiFDabRWTqSCIhbaxbl1owKxLIxrMuOFCoMgBw25iSNtGx2gyp-WKOC0YLrf6fbPXnZ1UMwLbO9PNKXUNzUc1PV66KjEm53DZPdnQgll8YZDvdqIaOlPe_i3ObA2rj373mZnDj7V3jRLKvh_hqm8_AKzDVMFqxXXV7jZeyzV1dCw7iij3CgLRzYqWGIaejfWRgtvT6gU4JyhY8x2lLnAiUCdW4kkl-c46MnvKzYsrQC9uGrBwajLiT3YtPrxPJy-ycC_QasclfkCsMjIAt3qAqNDKVWhlU_1vzrTIvBdFXiLIJolT03diZ0IQS5TisgIKGkFlJSAktZAWQT-ctd11YnkP_IrDVTSWi-N01ecLP378nf4eHDSPU6PO72jZZihB1cbTyvQmtze5avwwdxPhuPbtfoTYPDrrXH1DMr_QXs
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=Dynamic+Modification+of+Activation+Function+using+the+Backpropagation+Algorithm+in+the+Artificial+Neural+Networks&rft.jtitle=International+journal+of+advanced+computer+science+%26+applications&rft.au=Mercioni%2C+Marina+Adriana&rft.au=Tiron%2C+Alexandru&rft.au=Holban%2C+Stefan&rft.date=2019&rft.pub=Science+and+Information+%28SAI%29+Organization+Limited&rft.issn=2158-107X&rft.eissn=2156-5570&rft.volume=10&rft.issue=4&rft_id=info:doi/10.14569%2FIJACSA.2019.0100406
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2158-107X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2158-107X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2158-107X&client=summon