Deep learning on Sleptsov nets

Sleptsov nets are applied as a uniform language to specify models of unconventional computations and artificial intelligence systems. A technique for specification of neural networks, including multidimensional and multilayer networks of deep learning approach, using Sleptsov nets, is shown; the way...

Full description

Saved in:
Bibliographic Details
Published in:International journal of parallel, emergent and distributed systems Vol. 36; no. 6; pp. 535 - 548
Main Authors: Shmeleva, Tatiana R., Owsiński, Jan W., Lawan, Abdulmalik Ahmad
Format: Journal Article
Language:English
Published: Abingdon Taylor & Francis 02.11.2021
Taylor & Francis Ltd
Subjects:
Artificial intelligence
Deep learning
gradient descend
mass parallel computations
Multilayers
Neural network
Neural networks
Optimization
Real numbers
sigmoid
Sleptsov net
ISSN:1744-5760, 1744-5779
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Sleptsov nets are applied as a uniform language to specify models of unconventional computations and artificial intelligence systems. A technique for specification of neural networks, including multidimensional and multilayer networks of deep learning approach, using Sleptsov nets, is shown; the ways of specifying basic activation functions by Sleptsov net are discussed, the threshold and sigmoid functions implemented. A methodology of training neural networks is presented with the loss function minimisation, based on a run of a pair of interacting Sleptsov nets, the first net implementing the neural network based on data flow approach, while the second net solves the optimisation task by adjusting the weights of the first net by the gradient descend method. The optimising net uses the earlier developed technology of programming in Sleptsov nets with reverse control flow and the subnet call technique. Real numbers and arrays are represented as markings of a single place of a Sleptsov net. Hyperperformance is achieved because of the possibility of implementing mass parallel computations.
AbstractList Sleptsov nets are applied as a uniform language to specify models of unconventional computations and artificial intelligence systems. A technique for specification of neural networks, including multidimensional and multilayer networks of deep learning approach, using Sleptsov nets, is shown; the ways of specifying basic activation functions by Sleptsov net are discussed, the threshold and sigmoid functions implemented. A methodology of training neural networks is presented with the loss function minimisation, based on a run of a pair of interacting Sleptsov nets, the first net implementing the neural network based on data flow approach, while the second net solves the optimisation task by adjusting the weights of the first net by the gradient descend method. The optimising net uses the earlier developed technology of programming in Sleptsov nets with reverse control flow and the subnet call technique. Real numbers and arrays are represented as markings of a single place of a Sleptsov net. Hyperperformance is achieved because of the possibility of implementing mass parallel computations.
Author Lawan, Abdulmalik Ahmad
Shmeleva, Tatiana R.
Owsiński, Jan W.
Author_xml – sequence: 1
  givenname: Tatiana R.
  orcidid: 0000-0002-4799-3842
  surname: Shmeleva
  fullname: Shmeleva, Tatiana R.
  email: t.shmeleva@onat.edu.ua
  organization: Department of Computer Science, State University of Intelligent Technology and Telecommunications
– sequence: 2
  givenname: Jan W.
  orcidid: 0000-0002-2750-6584
  surname: Owsiński
  fullname: Owsiński, Jan W.
  organization: Systems Research Institute, Polish Academy of Sciences
– sequence: 3
  givenname: Abdulmalik Ahmad
  surname: Lawan
  fullname: Lawan, Abdulmalik Ahmad
  organization: Department of Computer Science, Kano University of Science and Technology
BookMark eNqFkE1LAzEQhoNUsK3-BGXB866TzWazixelfkLBg3oO2XxIyjZZk1Tpv7el1YMHPc0wvM878EzQyHmnETrFUGBo4AKzqqKshqKEEhe4rShQeoDG23tOGWtHP3sNR2gS4wKgKquajdHZjdZD1msRnHVvmXfZc6-HFP1H5nSKx-jQiD7qk_2cote725fZQz5_un-cXc9zSUiT8hYM6cpSVkq0xsiuYkaBJrShTDDWKSMkSK2N6JQkWqoOVFMrBqZpleo0I1N0vusdgn9f6Zj4wq-C27zkJW0wxkBasknRXUoGH2PQhg_BLkVYcwx8q4J_q-BbFXyvYsNd_uKkTSJZ71IQtv-XvtrR1hkfluLTh17xJNa9DyYIJ23k5O-KL3xfeUA
CitedBy_id crossref_primary_10_1016_j_ins_2022_11_098
Cites_doi 10.1109/ICASSP.2013.6638947
10.1007/BF02667189
10.1109/ACCESS.2021.3084995
10.1007/978-981-10-5209-5_1
10.3390/s20051515
10.1080/17445760.2012.662682
10.1109/TSMC.2015.2433892
10.1007/11785231_121
10.1007/s10559-012-9429-4
10.1177/1687814016640159
10.1109/TSMC.2015.2444414
10.1002/tee.22508
10.1007/s11047-010-9213-1
10.1177/0037549717709932
10.1109/5.726791
10.1109/ACCESS.2020.2999054
10.1016/j.mri.2019.05.028
10.1007/978-3-319-23111-2_12
10.1109/TNNLS.2021.3082304
10.3103/S0146411612070140
10.4018/978-1-5225-2255-3.ch672
10.1007/3-540-11981-7_5
10.1098/rsfs.2018.0029
10.1109/TPDS.2020.2990924
10.1080/00207160.2017.1283410
10.2172/4242290
10.1007/978-3-540-92910-9_58
10.1145/3133956.3134012
10.1109/ITNEC.2019.8729185
10.1109/TrustCom/BigDataSE.2018.00150
10.1126/science.1200520
10.1215/S0012-7094-36-00227-2
10.1142/7968
10.1134/S0005117914080025
10.1109/MSEC.2018.2888775
10.1109/TSMC.2012.2237549
ContentType Journal Article
Copyright 2021 Informa UK Limited, trading as Taylor & Francis Group 2021
2021 Informa UK Limited, trading as Taylor & Francis Group
Copyright_xml – notice: 2021 Informa UK Limited, trading as Taylor & Francis Group 2021
– notice: 2021 Informa UK Limited, trading as Taylor & Francis Group
DBID AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1080/17445760.2021.1945055
DatabaseName CrossRef
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList Computer and Information Systems Abstracts
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1744-5779
EndPage 548
ExternalDocumentID 10_1080_17445760_2021_1945055
1945055
Genre Research Article
GroupedDBID .7F
.QJ
0BK
0R~
29J
30N
4.4
5GY
AAENE
AAGDL
AAHIA
AAJMT
AALDU
AAMIU
AAPUL
AAQRR
ABCCY
ABFIM
ABHAV
ABLIJ
ABPAQ
ABPEM
ABTAI
ABXUL
ABXYU
ACGEJ
ACGFS
ACTIO
ADCVX
ADGTB
ADXPE
AEISY
AEOZL
AEPSL
AEYOC
AFKVX
AFRVT
AGDLA
AGMYJ
AHDZW
AIJEM
AIYEW
AJWEG
AKBVH
AKOOK
ALMA_UNASSIGNED_HOLDINGS
ALQZU
AQRUH
AQTUD
AVBZW
AWYRJ
BLEHA
CCCUG
CE4
CS3
DGEBU
DKSSO
EBS
E~A
E~B
GTTXZ
H13
HF~
HZ~
H~P
IPNFZ
J.P
KYCEM
LJTGL
M4Z
NA5
NX~
O9-
PQQKQ
RIG
RNANH
ROSJB
RTWRZ
S-T
SNACF
TASJS
TBQAZ
TDBHL
TEN
TFL
TFT
TFW
TNC
TTHFI
TUROJ
TWF
UT5
UU3
ZGOLN
~S~
AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c338t-90f3b22c4da9ffcb47fd0e35857a77bdfac0ceefabdc3ecdb0d86d70f89ddbe73
IEDL.DBID TFW
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000667609400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1744-5760
IngestDate Sun Nov 09 07:59:53 EST 2025
Sat Nov 29 02:32:40 EST 2025
Tue Nov 18 22:15:19 EST 2025
Mon Oct 20 23:47:39 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 6
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c338t-90f3b22c4da9ffcb47fd0e35857a77bdfac0ceefabdc3ecdb0d86d70f89ddbe73
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-4799-3842
0000-0002-2750-6584
PQID 2581110393
PQPubID 176139
PageCount 14
ParticipantIDs proquest_journals_2581110393
crossref_primary_10_1080_17445760_2021_1945055
crossref_citationtrail_10_1080_17445760_2021_1945055
informaworld_taylorfrancis_310_1080_17445760_2021_1945055
PublicationCentury 2000
PublicationDate 2021-11-02
PublicationDateYYYYMMDD 2021-11-02
PublicationDate_xml – month: 11
  year: 2021
  text: 2021-11-02
  day: 02
PublicationDecade 2020
PublicationPlace Abingdon
PublicationPlace_xml – name: Abingdon
PublicationTitle International journal of parallel, emergent and distributed systems
PublicationYear 2021
Publisher Taylor & Francis
Taylor & Francis Ltd
Publisher_xml – name: Taylor & Francis
– name: Taylor & Francis Ltd
References CIT0030
CIT0032
CIT0034
Adamatzky A (CIT0005) 2005
CIT0035
CIT0038
CIT0037
CIT0039
CIT0043
CIT0042
CIT0044
Sharp JA. (CIT0049) 1992
Minsky ML. (CIT0013) 1967
Peterson JL. (CIT0045) 1981
CIT0003
CIT0047
CIT0046
Shokri R (CIT0036) 2016
CIT0004
CIT0048
CIT0007
CIT0006
CIT0009
Chollet F. (CIT0054) 2018
CIT0008
CIT0050
CIT0052
CIT0051
CIT0010
CIT0053
CIT0012
CIT0011
CIT0055
Chollet F. (CIT0033) 2018
Unconventional Computing (CIT0001) 2018
CIT0014
CIT0016
CIT0015
CIT0018
Bellet A (CIT0040) 2018
CIT0017
CIT0019
CIT0021
CIT0020
CIT0023
CIT0022
Arık SÖ (CIT0031) 2017; 1
Zaitsev DA. (CIT0026) 2018; 13
Cook M. (CIT0002) 2004; 15
CIT0025
CIT0024
Sani MA (CIT0041) 2021; 40
CIT0027
CIT0029
CIT0028
References_xml – ident: CIT0015
– ident: CIT0030
  doi: 10.1109/ICASSP.2013.6638947
– ident: CIT0016
  doi: 10.1007/BF02667189
– start-page: 61
  volume-title: Deep learning with python
  year: 2018
  ident: CIT0054
– volume-title: Petri net theory and the modeling of systems
  year: 1981
  ident: CIT0045
– ident: CIT0020
  doi: 10.1109/ACCESS.2021.3084995
– ident: CIT0032
  doi: 10.1007/978-981-10-5209-5_1
– ident: CIT0050
  doi: 10.3390/s20051515
– volume-title: A volume in the encyclopedia of complexity and systems science
  year: 2018
  ident: CIT0001
– ident: CIT0029
– ident: CIT0009
  doi: 10.1080/17445760.2012.662682
– ident: CIT0018
  doi: 10.1109/TSMC.2015.2433892
– ident: CIT0012
  doi: 10.1007/11785231_121
– volume: 40
  start-page: 91
  issue: 1
  year: 2021
  ident: CIT0041
  publication-title: Int J Comput (IJC)
– ident: CIT0022
  doi: 10.1007/s10559-012-9429-4
– ident: CIT0037
– ident: CIT0048
  doi: 10.1177/1687814016640159
– ident: CIT0017
  doi: 10.1109/TSMC.2015.2444414
– ident: CIT0023
  doi: 10.1002/tee.22508
– ident: CIT0003
  doi: 10.1007/s11047-010-9213-1
– ident: CIT0028
  doi: 10.1177/0037549717709932
– ident: CIT0052
  doi: 10.1109/5.726791
– ident: CIT0019
  doi: 10.1109/ACCESS.2020.2999054
– ident: CIT0039
  doi: 10.1016/j.mri.2019.05.028
– ident: CIT0053
– ident: CIT0027
  doi: 10.1007/978-3-319-23111-2_12
– ident: CIT0044
  doi: 10.1109/TNNLS.2021.3082304
– ident: CIT0025
  doi: 10.3103/S0146411612070140
– ident: CIT0047
  doi: 10.4018/978-1-5225-2255-3.ch672
– ident: CIT0046
  doi: 10.1007/3-540-11981-7_5
– ident: CIT0008
  doi: 10.1098/rsfs.2018.0029
– start-page: 473
  volume-title: International Conference on Artificial Intelligence and Statistics
  year: 2018
  ident: CIT0040
– ident: CIT0043
  doi: 10.1109/TPDS.2020.2990924
– ident: CIT0021
  doi: 10.1080/00207160.2017.1283410
– start-page: 3
  volume-title: Deep learning with python
  year: 2018
  ident: CIT0033
– ident: CIT0011
  doi: 10.2172/4242290
– volume-title: Computation: finite and Infinite machines
  year: 1967
  ident: CIT0013
– volume-title: Data flow computing: theory and practice
  year: 1992
  ident: CIT0049
– ident: CIT0007
  doi: 10.1007/978-3-540-92910-9_58
– ident: CIT0034
  doi: 10.1145/3133956.3134012
– ident: CIT0042
  doi: 10.1109/ITNEC.2019.8729185
– ident: CIT0010
– ident: CIT0038
  doi: 10.1109/TrustCom/BigDataSE.2018.00150
– ident: CIT0004
  doi: 10.1126/science.1200520
– start-page: 909
  volume-title: 2015 53rd Annu. Allert. Conf. Commun. Control. Comput. Allert. 2015
  year: 2016
  ident: CIT0036
– volume-title: Reaction-diffusion computers
  year: 2005
  ident: CIT0005
– ident: CIT0014
  doi: 10.1215/S0012-7094-36-00227-2
– volume: 1
  start-page: 264
  year: 2017
  ident: CIT0031
  publication-title: 34th int Conf Mach Learn ICML
– ident: CIT0051
– volume: 13
  start-page: 121
  issue: 1
  year: 2018
  ident: CIT0026
  publication-title: J Cell Autom
– volume: 15
  start-page: 1
  year: 2004
  ident: CIT0002
  publication-title: Complex Syst
– ident: CIT0006
  doi: 10.1142/7968
– ident: CIT0055
  doi: 10.1134/S0005117914080025
– ident: CIT0035
  doi: 10.1109/MSEC.2018.2888775
– ident: CIT0024
  doi: 10.1109/TSMC.2012.2237549
SSID ssj0042467
Score 2.2294767
Snippet Sleptsov nets are applied as a uniform language to specify models of unconventional computations and artificial intelligence systems. A technique for...
SourceID proquest
crossref
informaworld
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 535
SubjectTerms Artificial intelligence
Deep learning
gradient descend
mass parallel computations
Multilayers
Neural network
Neural networks
Optimization
Real numbers
sigmoid
Sleptsov net
Title Deep learning on Sleptsov nets
URI https://www.tandfonline.com/doi/abs/10.1080/17445760.2021.1945055
https://www.proquest.com/docview/2581110393
Volume 36
WOSCitedRecordID wos000667609400001&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: PRVAWR
  databaseName: Taylor & Francis Online Journals
  customDbUrl:
  eissn: 1744-5779
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0042467
  issn: 1744-5760
  databaseCode: TFW
  dateStart: 20050301
  isFulltext: true
  titleUrlDefault: https://www.tandfonline.com
  providerName: Taylor & Francis
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LSwMxEA5SPHixPrFaZQ9eU9Ns2uweRS0epAhW7S3kMRGhbEt37e83yWbFItKDHvcwIUwyr83M9yF0qRW1kuUcU24Ae_QRZ3Ogseayb_yrIwv8KS8PfDzOptP8MXYTlrGt0tfQtgaKCL7aG7dUZdMRd-WSaObSZOKqO9rvuSrcRXE_Zu5CvzfNyei18cWMssAh6yWwF2lmeH5bZS06rWGX_vDVIQCN2v-w9T20G7PP5Lq-LvtoC4oD1G6YHZJo6Ifo4hZgkURGibdkXiRPM1hU5XyVFFCVR-h5dDe5uceRSQFrV4JWOCc2VZRqZmRurVaMW0MgdaUCl5wrY6UmLlpaqYxOQRtFTDY0nNgsN0YBT49Rq5gXcOJnvMHAkHDNCLhUayitq0MHLq0LD3Rs0EGs0aDQEWbcs13MRD-ikTY6EF4HIuqgg3pfYosaZ2OTQP79eEQVfnDYmo1EpBtku81ZimiypaCDzPl9P6p8-oelz9CO_wzTirSLWtXyA87Rtl5V7-XyIlzOT0cR3Y8
linkProvider Taylor & Francis
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3NT8IwFG8UTfQifkYUcQevw9J1dDsalWBELqJya7b21ZiQQdjk77ftOgMxhoOem9c0r31fbd_vh9CVSIlKaMx8wiT4Bn1E2xwIX7CkI82rI7X8Ka8DNhxG43G83AtjvlWaGlqVQBHWVxvjNpfR1Ze4a51FU50nY13ekU5bl-E6jIebaCvUsdbg5496b5U3poRaFlkj4huZqovnt2lW4tMKeukPb21DUK_-H4vfR3suAfVuyhNzgDYgO0T1itzBc7Z-hFp3ADPPkUq8e9PMe57ArMinCy-DIj9GL7370W3fd2QKvtBVaOHHWAUpIYLKJFZKpJQpiSHQ1QJLGEulSgTWAVMlqRQBCJliGXUlwyqKpUyBBSeolk0zODVt3iChi5mgGHS21U2ULkVDndnZNzoaNhCtVMiFQxo3hBcT3nGApJUOuNEBdzpooPa32KyE2lgnEC_vDy_sHYcqCUl4sEa2WW0md1abcxJG2vWbbuWzP0x9iXb6o6cBHzwMH8_RrhmyzYukiWrF_BMu0LZYFB_5vGVP6hdrCeG5
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3NS8MwFA86Rbw4P3E6Zw9eO7M0bdqjOIviGAOn7hbafIgw2rLW_f0maSoOkR302vJCecn7at77_QC4YimSCY6IiwgXrkYfUTYnmMtIMuD61hEb_pSXERmPw9ksmthuwtK2VeoaWtZAEcZXa-MuuGw64q5VEo1VmgxVdYcGfVWFqyjub4It9SzQh3wavzbOGCNsSGS1iKtlmiGe35ZZCU8r4KU_nLWJQHH7H759H-zZ9NO5qc_LAdgQ2SFoN9QOjrX0I9AbClE4llLizckz52kuiqrMl04mqvIYPMd309t711IpuEzVoJUbQemlCDHMk0hKlmIiORSeqhVIQkjKZcKgCpcySTnzBOMp5GHACZRhxHkqiHcCWlmeiVM95C24CCBhGAqVawWJVIWor_I6c0OH_Q7AjQYpszjjmu5iTgcWjrTRAdU6oFYHHdD_EitqoI11AtH37aGV-cMhazoS6q2R7TZ7Sa3NlhT5oXL8elb57A9LX4KdyTCmo4fx4znY1W_M5CLqgla1-BAXYJstq_dy0TPn9BPOQ-Br
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+on+Sleptsov+nets&rft.jtitle=International+journal+of+parallel%2C+emergent+and+distributed+systems&rft.au=Shmeleva%2C+Tatiana+R.&rft.au=Owsi%C5%84ski%2C+Jan+W.&rft.au=Lawan%2C+Abdulmalik+Ahmad&rft.date=2021-11-02&rft.pub=Taylor+%26+Francis&rft.issn=1744-5760&rft.eissn=1744-5779&rft.volume=36&rft.issue=6&rft.spage=535&rft.epage=548&rft_id=info:doi/10.1080%2F17445760.2021.1945055&rft.externalDocID=1945055
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1744-5760&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1744-5760&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1744-5760&client=summon