Review and comparative analysis of machine learning libraries for machine learning

The article is an overview. We carry out the comparison of actual machine learning libraries that can be used the neural networks development. The first part of the article gives a brief description of TensorFlow, PyTorch, Theano, Keras, SciKit Learn libraries, SciPy library stack. An overview of th...

Full description

Saved in:
Bibliographic Details
Published in:Discrete and continuous models and applied computational science Vol. 27; no. 4; pp. 305 - 315
Main Authors: Gevorkyan, Migran N., Demidova, Anastasia V., Demidova, Tatiana S., Sobolev, Anton A.
Format: Journal Article
Language:English
Published: Peoples’ Friendship University of Russia (RUDN University) 15.12.2019
Subjects:
machine learning
mnist
neural networks
pytorch
tensorflow
ISSN:2658-4670, 2658-7149
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The article is an overview. We carry out the comparison of actual machine learning libraries that can be used the neural networks development. The first part of the article gives a brief description of TensorFlow, PyTorch, Theano, Keras, SciKit Learn libraries, SciPy library stack. An overview of the scope of these libraries and the main technical characteristics, such as performance, supported programming languages, the current state of development is given. In the second part of the article, a comparison of five libraries is carried out on the example of a multilayer perceptron, which is applied to the problem of handwritten digits recognizing. This problem is well known and well suited for testing different types of neural networks. The study time is compared depending on the number of epochs and the accuracy of the classifier. The results of the comparison are presented in the form of graphs of training time and accuracy depending on the number of epochs and in tabular form.
AbstractList The article is an overview. We carry out the comparison of actual machine learning libraries that can be used the neural networks development. The first part of the article gives a brief description of TensorFlow, PyTorch, Theano, Keras, SciKit Learn libraries, SciPy library stack. An overview of the scope of these libraries and the main technical characteristics, such as performance, supported programming languages, the current state of development is given. In the second part of the article, a comparison of five libraries is carried out on the example of a multilayer perceptron, which is applied to the problem of handwritten digits recognizing. This problem is well known and well suited for testing different types of neural networks. The study time is compared depending on the number of epochs and the accuracy of the classifier. The results of the comparison are presented in the form of graphs of training time and accuracy depending on the number of epochs and in tabular form.
Author Gevorkyan, Migran N.
Demidova, Tatiana S.
Demidova, Anastasia V.
Sobolev, Anton A.
Author_xml – sequence: 1
  givenname: Migran N.
  surname: Gevorkyan
  fullname: Gevorkyan, Migran N.
– sequence: 2
  givenname: Anastasia V.
  surname: Demidova
  fullname: Demidova, Anastasia V.
– sequence: 3
  givenname: Tatiana S.
  surname: Demidova
  fullname: Demidova, Tatiana S.
– sequence: 4
  givenname: Anton A.
  surname: Sobolev
  fullname: Sobolev, Anton A.
BookMark eNqNkMtKAzEUhoNUsNa-wyzcRnOfBNxo8VIoCEXX4SSTqSnTSckUpW_vTFtc6MbVufznfIvvEo3a1AaErim5YYwrfsuU1FiokmBGqMGsxAJzIjGn8gyND2lJhRmd-uHyAk27bk0IYbrkkqgxWi7DZwxfBbRV4dNmCxl28TP0MzT7LnZFqosN-I_YhqIJkNvYroomugw5hq6oU_4TX6HzGpouTE91gt6fHt9mL3jx-jyf3S-w54RJ7GVgwAUoQ1VFldOO6FIap7gSlBMwotLMSaDShJJr4kojSBWqunLCBen4BM2P3CrB2m5z3EDe2wTRHhYpryzkXfRNsCQIVWtTacG5IN5poLXUVHJWe0NN6Fl3R5bPqetyqH94lNiDbjtItINEO-i2rLTC9rptr7t_f_j17uOuF5naXYbY_A_yDSgWiTw
CitedBy_id crossref_primary_10_1088_1742_6596_1801_1_012008
crossref_primary_10_1016_j_biortech_2022_128421
crossref_primary_10_3389_fonc_2022_1023110
crossref_primary_10_1145_3678168
crossref_primary_10_1007_s11182_024_03124_1
crossref_primary_10_1134_S1547477124701413
crossref_primary_10_1007_s12155_025_10864_6
crossref_primary_10_1016_j_jbusres_2025_115571
crossref_primary_10_22630_MIBE_2021_22_1_3
crossref_primary_10_35784_jcsi_2693
crossref_primary_10_3389_fpsyg_2022_843427
crossref_primary_10_1155_2024_5653690
crossref_primary_10_1145_3705309
crossref_primary_10_1109_TR_2024_3455390
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.22363/2658-4670-2019-27-4-305-315
DatabaseName CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2658-7149
EndPage 315
ExternalDocumentID oai_doaj_org_article_0e46f89d843340cb8a1f581532fc919e
10_22363_2658_4670_2019_27_4_305_315
GroupedDBID AAFWJ
AAYXX
AFPKN
ALMA_UNASSIGNED_HOLDINGS
CITATION
GROUPED_DOAJ
VCL
VIT
ID FETCH-LOGICAL-c3025-c5e2a34a6916d16b8b08759b6364130a94d82b5a159e7380b7940dedfdb4be5b3
IEDL.DBID DOA
ISSN 2658-4670
IngestDate Fri Oct 03 12:45:45 EDT 2025
Tue Nov 18 21:22:00 EST 2025
Sat Nov 29 02:22:26 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Language English
License http://creativecommons.org/licenses/by/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3025-c5e2a34a6916d16b8b08759b6364130a94d82b5a159e7380b7940dedfdb4be5b3
OpenAccessLink https://doaj.org/article/0e46f89d843340cb8a1f581532fc919e
PageCount 11
ParticipantIDs doaj_primary_oai_doaj_org_article_0e46f89d843340cb8a1f581532fc919e
crossref_primary_10_22363_2658_4670_2019_27_4_305_315
crossref_citationtrail_10_22363_2658_4670_2019_27_4_305_315
PublicationCentury 2000
PublicationDate 2019-12-15
PublicationDateYYYYMMDD 2019-12-15
PublicationDate_xml – month: 12
  year: 2019
  text: 2019-12-15
  day: 15
PublicationDecade 2010
PublicationTitle Discrete and continuous models and applied computational science
PublicationYear 2019
Publisher Peoples’ Friendship University of Russia (RUDN University)
Publisher_xml – name: Peoples’ Friendship University of Russia (RUDN University)
SSID ssj0002873506
ssib050730783
Score 2.3226254
SecondaryResourceType review_article
Snippet The article is an overview. We carry out the comparison of actual machine learning libraries that can be used the neural networks development. The first part...
SourceID doaj
crossref
SourceType Open Website
Enrichment Source
Index Database
StartPage 305
SubjectTerms machine learning
mnist
neural networks
pytorch
tensorflow
Title Review and comparative analysis of machine learning libraries for machine learning
URI https://doaj.org/article/0e46f89d843340cb8a1f581532fc919e
Volume 27
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2658-7149
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002873506
  issn: 2658-4670
  databaseCode: DOA
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources (ISSN International Center)
  customDbUrl:
  eissn: 2658-7149
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib050730783
  issn: 2658-4670
  databaseCode: M~E
  dateStart: 20190101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA6yiOhBfOL6Ioe9lm3zaFM8qbh4kEVEZW8hSRNRtCvr6u93pu3Wigc9eGxKSvjyJTPJTL8hZKAyLoJTmFZlTSTAIYhM4PjrU0hSZV1WR0zvr7LxWE0m-XWn1BfmhNXywDVww9iLNKi8UIJzETurTBKkgnXKgsuT3OPuG2d55zAFTJJI3EV86qm6Qsq4rAptMjC5EewO8QoZYB404ykfto1AmiSHgUYYLsAQsfxmrzqy_pX9GW2Q9cZxpKf1gDfJki-3yFpHTnCb3NQX_dSUBXVfqt7wXAuP0GmgL1XypKdNtYgH2p6XKbivP17vkLvRxe35ZdTUTIgcx8q0TnpmuDApuH1FklplUbI-tylP0VyZXBSKWWnAi_EwD7GF9RgXvgiFFdZLy3dJr5yWfo9QoRgPisH-ZyzKstnMg3cWjIR58HHq--RkgYx2jaA41rV41nCwqHDViKtGXDXiqlmmhQZcNeDaJ7Lt_VoLa_yx3xlOQtsH5bGrBiCNbkijfyPN_n985ICsVmxJWJTIQ9Kbz979EVl2H_PHt9lxxcdPlznZrQ
linkProvider Directory of Open Access Journals
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=Review+and+comparative+analysis+of+machine+learning+libraries+for+machine+learning&rft.jtitle=Discrete+and+continuous+models+and+applied+computational+science&rft.au=Migran+N.+Gevorkyan&rft.au=Anastasia+V.+Demidova&rft.au=Tatiana+S.+Demidova&rft.au=Anton+A.+Sobolev&rft.date=2019-12-15&rft.pub=Peoples%E2%80%99+Friendship+University+of+Russia+%28RUDN+University%29&rft.issn=2658-4670&rft.eissn=2658-7149&rft.volume=27&rft.issue=4&rft.spage=305&rft.epage=315&rft_id=info:doi/10.22363%2F2658-4670-2019-27-4-305-315&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_0e46f89d843340cb8a1f581532fc919e
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2658-4670&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2658-4670&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2658-4670&client=summon