Convolutional neural networks based on fractional-order momentum for parameter training

This paper proposes a parameter training method via the fractional-order momentum for convolutional neural networks (CNNs). To update the parameters of CNNs more smoothly, the parameter training method via the fractional-order momentum is proposed based on the Grünwald-Letnikov (G-L) difference oper...

Full description

Saved in:
Bibliographic Details
Published inNeurocomputing (Amsterdam) Vol. 449; pp. 85 - 99
Main Authors Kan, Tao, Gao, Zhe, Yang, Chuang, Jian, Jing
Format Journal Article
LanguageEnglish
Published Elsevier B.V 18.08.2021
Subjects
Online AccessGet full text
ISSN0925-2312
1872-8286
DOI10.1016/j.neucom.2021.03.075

Cover

Abstract This paper proposes a parameter training method via the fractional-order momentum for convolutional neural networks (CNNs). To update the parameters of CNNs more smoothly, the parameter training method via the fractional-order momentum is proposed based on the Grünwald-Letnikov (G-L) difference operation. The stochastic classical momentum (SCM) algorithm and adaptive moment (Adam) estimation algorithm are improved by replacing the integer-order difference with the fractional-order difference. Meanwhile, the linear and the nonlinear methods are discussed to adjust the fractional-order. Therefore, the proposed methods can improve the flexibility and the adaptive ability of CNN parameters. We analyze the validity of the methods by using MNIST dataset and CIFAR-10 dataset, and the experimental results show that the proposed methods can improve the recognition accuracy and the learning convergence speed of CNNs compared with the traditional SCM and Adam methods.
AbstractList This paper proposes a parameter training method via the fractional-order momentum for convolutional neural networks (CNNs). To update the parameters of CNNs more smoothly, the parameter training method via the fractional-order momentum is proposed based on the Grünwald-Letnikov (G-L) difference operation. The stochastic classical momentum (SCM) algorithm and adaptive moment (Adam) estimation algorithm are improved by replacing the integer-order difference with the fractional-order difference. Meanwhile, the linear and the nonlinear methods are discussed to adjust the fractional-order. Therefore, the proposed methods can improve the flexibility and the adaptive ability of CNN parameters. We analyze the validity of the methods by using MNIST dataset and CIFAR-10 dataset, and the experimental results show that the proposed methods can improve the recognition accuracy and the learning convergence speed of CNNs compared with the traditional SCM and Adam methods.
Author Kan, Tao
Gao, Zhe
Yang, Chuang
Jian, Jing
Author_xml – sequence: 1
  givenname: Tao
  surname: Kan
  fullname: Kan, Tao
  organization: School of Mathematics, Liaoning University, Shenyang 110036, PR China
– sequence: 2
  givenname: Zhe
  surname: Gao
  fullname: Gao, Zhe
  email: gaozhe@lnu.edu.cn
  organization: School of Mathematics, Liaoning University, Shenyang 110036, PR China
– sequence: 3
  givenname: Chuang
  surname: Yang
  fullname: Yang, Chuang
  organization: School of Mathematics, Liaoning University, Shenyang 110036, PR China
– sequence: 4
  givenname: Jing
  surname: Jian
  fullname: Jian, Jing
  organization: School of Mathematics, Liaoning University, Shenyang 110036, PR China
BookMark eNqFkEFLwzAYhoNMcJv-Aw_9A61J2iWtB0GGTmHgRfEY0uSLZLbJSLKJ_97WevKgpxc-vueF91mgmfMOELokuCCYsKtd4eCgfF9QTEmBywLz1Qmak5rTvKY1m6E5bugqpyWhZ2gR4w5jwglt5uh17d3Rd4dkvZNdNvSE70gfPrzHrJURdOZdZoJU00_ug4aQ9b4Hlw59ZnzI9jLIHtJwTkFaZ93bOTo1sotw8ZNL9HJ_97x-yLdPm8f17TZXJWYp55oYqQkY3ba6qjVnEjSuOC0rqIA1uOGNMiAxk3wYQtrWsEYqiktgZGDKJaqmXhV8jAGM2Afby_ApCBajHLETkxwxyhG4FIOcAbv-hSmb5DhwHND9B99MMAzDjhaCiMqCU6BtAJWE9vbvgi9tcoho
CitedBy_id crossref_primary_10_1016_j_chaos_2022_112611
crossref_primary_10_3390_math11020316
crossref_primary_10_1016_j_chaos_2025_116154
crossref_primary_10_1016_j_eswa_2023_121659
crossref_primary_10_3390_fractalfract6070348
crossref_primary_10_1109_TCE_2024_3371928
crossref_primary_10_1016_j_compeleceng_2023_108696
crossref_primary_10_1155_2021_9096727
crossref_primary_10_1007_s00521_021_06765_2
crossref_primary_10_1007_s11063_024_11571_7
crossref_primary_10_1016_j_neunet_2024_106970
Cites_doi 10.14569/IJACSA.2020.0110719
10.1016/j.neucom.2019.04.087
10.2478/v10006-009-0022-6
10.1016/j.neucom.2019.07.016
10.1016/j.neucom.2019.10.017
10.1016/j.neucom.2019.04.057
10.3390/sym12050683
10.1162/neco.1989.1.4.541
10.1016/j.neucom.2019.10.048
10.1016/j.jvcir.2018.06.019
10.1109/5.726791
10.1016/j.amc.2018.10.037
10.1109/TNNLS.2013.2280458
10.1016/j.neucom.2020.07.036
10.1016/j.patrec.2019.12.013
10.1109/TITS.2019.2900385
10.1016/j.isprsjprs.2020.08.001
10.1016/j.neucom.2017.01.023
10.1016/j.neucom.2020.02.005
10.1109/TNNLS.2015.2506738
10.1016/S0893-6080(98)00116-6
ContentType Journal Article
Copyright 2021 Elsevier B.V.
Copyright_xml – notice: 2021 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.neucom.2021.03.075
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1872-8286
EndPage 99
ExternalDocumentID 10_1016_j_neucom_2021_03_075
S0925231221004616
GroupedDBID ---
--K
--M
.DC
.~1
0R~
123
1B1
1~.
1~5
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JM
9JN
AABNK
AACTN
AADPK
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXLA
AAXUO
AAYFN
ABBOA
ABCQJ
ABFNM
ABJNI
ABMAC
ABYKQ
ACDAQ
ACGFS
ACRLP
ACZNC
ADBBV
ADEZE
AEBSH
AEKER
AENEX
AFKWA
AFTJW
AFXIZ
AGHFR
AGUBO
AGWIK
AGYEJ
AHHHB
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
AXJTR
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
IHE
J1W
KOM
LG9
M41
MO0
MOBAO
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
ROL
RPZ
SDF
SDG
SDP
SES
SPC
SPCBC
SSN
SSV
SSZ
T5K
ZMT
~G-
29N
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADJOM
ADMUD
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EJD
FEDTE
FGOYB
HLZ
HVGLF
HZ~
R2-
SBC
SEW
WUQ
XPP
~HD
ID FETCH-LOGICAL-c306t-7d1fad1efdbbd48d76aed047234e4e690979cfea06a72861bbf69ac203e61dbb3
IEDL.DBID .~1
ISSN 0925-2312
IngestDate Thu Apr 24 22:55:17 EDT 2025
Thu Oct 16 04:41:59 EDT 2025
Fri Feb 23 02:44:20 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords 99-00
Fractional-order difference
00-01
MNIST
Momentum
CIFAR-10
Convolutional neural networks
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c306t-7d1fad1efdbbd48d76aed047234e4e690979cfea06a72861bbf69ac203e61dbb3
PageCount 15
ParticipantIDs crossref_primary_10_1016_j_neucom_2021_03_075
crossref_citationtrail_10_1016_j_neucom_2021_03_075
elsevier_sciencedirect_doi_10_1016_j_neucom_2021_03_075
PublicationCentury 2000
PublicationDate 2021-08-18
PublicationDateYYYYMMDD 2021-08-18
PublicationDate_xml – month: 08
  year: 2021
  text: 2021-08-18
  day: 18
PublicationDecade 2020
PublicationTitle Neurocomputing (Amsterdam)
PublicationYear 2021
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References LeCun, Bottou, Bengio, Haffner (b0045) 1998; 86
He, Gong, Fan (b0075) 2019
Liu, Li, Wu, Cao, Hao, Xian (b0080) 2020; 378
Diederik, Jimmy (b0130) 2015
M.H. Zhou, Y. Feng, C. Xue, F.L. Han, Deep convolutional neural network based fractional-order terminal sliding-mode control for robotic manipulators, Neurocomputing, doi:10.1016/j.neucom.2019.04.087.
Qian (b0145) 1999; 12
Sui, Z, Wei, Bi, Wu, Pan, Yin, Zhang (b0065) 2017; 237
Wei, Jiang, Li, Li, Jia, Li (b0030) 2020; 21
LeCun, Boser, Denker, Henderson (b0040) 1989; 1
Chanthorn, Rajchakit, Humphries, Kaewmesri, Sriraman, Lim (b0095) 2020; 12
Aqab, Tariq (b0005) 2020; 11
Zhang, Huang, Tian (b0010) 2020; 131
Bottou (b0140) 2010
Sierociuk, Dzielinski (b0150) 2006; 1
Johnson, Zhang (b0115) 2013
Wu, Weng, Chen, Lu (b0070) 2018; 55
Zhuang, Zhang, Pan, Ni, Xu, Yang, Zhang (b0015) 2019; 358
Simonyan, Zisserman (b0055) 2015
Xi, Hopkinson, Rood, Peddle (b0020) 2020; 168
Wang, Deng (b0035) 2020; 393
John, Elad, Yoram (b0125) 2011; 12
Sheng, Wei, Chen, Wang (b0105) 2020; 408
Zhao, Luo (b0135) 2019; 346
Rajchakit, Chanthorn, Niezabitowski, Raja, Baleanu, Pratap (b0085) 2020; 417
Buslowicz, Kaczorek (b0155) 2009; 19
Krizhevsky, Sutskever, Hinton (b0050) 2012
Szegedy, Liu, Jia, Sermant, Reed, Anguelov, Erhan, Vanhoucke, Rabinovich (b0060) 2015
Zhu, Sun, Cao, Wang, Wu, Yang, Ye (b0025) 2019; 365
Wu, Zeng (b0100) 2014; 25
Botev, Lever, Barber (b0120) 2017
Wu, Zeng (b0090) 2017; 28
Wu (10.1016/j.neucom.2021.03.075_b0090) 2017; 28
Chanthorn (10.1016/j.neucom.2021.03.075_b0095) 2020; 12
Johnson (10.1016/j.neucom.2021.03.075_b0115) 2013
Xi (10.1016/j.neucom.2021.03.075_b0020) 2020; 168
Sierociuk (10.1016/j.neucom.2021.03.075_b0150) 2006; 1
Zhuang (10.1016/j.neucom.2021.03.075_b0015) 2019; 358
He (10.1016/j.neucom.2021.03.075_b0075) 2019
Bottou (10.1016/j.neucom.2021.03.075_b0140) 2010
Wu (10.1016/j.neucom.2021.03.075_b0100) 2014; 25
Qian (10.1016/j.neucom.2021.03.075_b0145) 1999; 12
John (10.1016/j.neucom.2021.03.075_b0125) 2011; 12
Wu (10.1016/j.neucom.2021.03.075_b0070) 2018; 55
Zhang (10.1016/j.neucom.2021.03.075_b0010) 2020; 131
Aqab (10.1016/j.neucom.2021.03.075_b0005) 2020; 11
Liu (10.1016/j.neucom.2021.03.075_b0080) 2020; 378
Sui (10.1016/j.neucom.2021.03.075_b0065) 2017; 237
Wang (10.1016/j.neucom.2021.03.075_b0035) 2020; 393
Botev (10.1016/j.neucom.2021.03.075_b0120) 2017
LeCun (10.1016/j.neucom.2021.03.075_b0045) 1998; 86
10.1016/j.neucom.2021.03.075_b0110
Krizhevsky (10.1016/j.neucom.2021.03.075_b0050) 2012
LeCun (10.1016/j.neucom.2021.03.075_b0040) 1989; 1
Zhao (10.1016/j.neucom.2021.03.075_b0135) 2019; 346
Szegedy (10.1016/j.neucom.2021.03.075_b0060) 2015
Sheng (10.1016/j.neucom.2021.03.075_b0105) 2020; 408
Zhu (10.1016/j.neucom.2021.03.075_b0025) 2019; 365
Wei (10.1016/j.neucom.2021.03.075_b0030) 2020; 21
Rajchakit (10.1016/j.neucom.2021.03.075_b0085) 2020; 417
Diederik (10.1016/j.neucom.2021.03.075_b0130) 2015
Buslowicz (10.1016/j.neucom.2021.03.075_b0155) 2009; 19
Simonyan (10.1016/j.neucom.2021.03.075_b0055) 2015
References_xml – volume: 365
  start-page: 191
  year: 2019
  end-page: 200
  ident: b0025
  article-title: TA-CNN: two-way attention models in deep convolutional neural network for plant recognition
  publication-title: Neurocomputing
– volume: 28
  start-page: 206
  year: 2017
  end-page: 217
  ident: b0090
  article-title: Global mittag-leffler stabilization of fractional-order memristive neural networks
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
– volume: 168
  start-page: 1
  year: 2020
  end-page: 16
  ident: b0020
  article-title: See the forest and the trees: effective machine and deep learning algorithms for wood filtering and tree species classification from terrestrial laser scanning
  publication-title: Isprs Journal of Photogrammetry and Remote Sensing
– start-page: 1
  year: 2015
  end-page: 15
  ident: b0130
  article-title: A method for stochastic optimization
  publication-title: Proceedings of International Conference on Learning Representations
– start-page: 913
  year: 2019
  end-page: 921
  ident: b0075
  article-title: Optimize deep convolutional neural network with ternarized weights and high accuracy
  publication-title: Proceedings of 2019 IEEE Winter Conference on Applications of Computer Vision (Wacv)
– volume: 378
  start-page: 45
  year: 2020
  end-page: 53
  ident: b0080
  article-title: Eye localization based on weight binarization cascade convolution neural network
  publication-title: Neurocomputing
– volume: 86
  start-page: 2278
  year: 1998
  end-page: 2324
  ident: b0045
  article-title: Gradient-based learning applied to document recognition
  publication-title: Proceedings of the IEEE
– volume: 346
  start-page: 531
  year: 2019
  end-page: 544
  ident: b0135
  article-title: Representations of acting processes and memory effects: General fractional derivative and its application to theory of heat conduction with finite wave speeds
  publication-title: Applied Mathematics and Computation
– start-page: 1097
  year: 2012
  end-page: 1105
  ident: b0050
  article-title: classification with deep convolutional neural networks
  publication-title: 2012 Neural Information Processing Systems (NIPS), Lake Tahoe, USA
– volume: 55
  start-page: 424
  year: 2018
  end-page: 432
  ident: b0070
  article-title: Feedback weight convolutional neural network for gait recognition
  publication-title: Journal of Visual Communication and Image Representation
– volume: 1
  start-page: 129
  year: 2006
  end-page: 140
  ident: b0150
  article-title: Fractional Kalman filter algorithm for the states, parameters and order of fractional system estimation
  publication-title: International Journal of Applied Mathematics and Computer Science
– start-page: 1
  year: 2015
  end-page: 9
  ident: b0060
  article-title: Going deeper with convolutions
  publication-title: 2015 IEEE Conference on Computer Vision and Pattern Recognization (CVPR), Boston, USA
– volume: 25
  start-page: 690
  year: 2014
  end-page: 703
  ident: b0100
  article-title: Lagrange stability of memristive neural networks with discrete and distributed delays
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
– start-page: 1899
  year: 2017
  end-page: 1903
  ident: b0120
  article-title: Nesterov’s accelerated gradient and momentum as approximations to regularised update descent
  publication-title: Proceeding of the 30th International Joint Conference on Neural Networks, Alaska, USA
– volume: 21
  start-page: 947
  year: 2020
  end-page: 958
  ident: b0030
  article-title: Defect detection of pantograph slide based on deep learning and image processing technology
  publication-title: IEEE Transactions on Intelligent Transportation Systems
– volume: 12
  year: 2020
  ident: b0095
  article-title: A delay-dividing approach to robust stability of uncertain stochastic complex-valued hopfield delayed neural networks
  publication-title: Symmetry
– volume: 237
  start-page: 332
  year: 2017
  end-page: 341
  ident: b0065
  article-title: Choroid segmentation from optical coherence tomography with graph-edge weights learned from deep convolutional neural networks
  publication-title: Neurocomputing
– reference: M.H. Zhou, Y. Feng, C. Xue, F.L. Han, Deep convolutional neural network based fractional-order terminal sliding-mode control for robotic manipulators, Neurocomputing, doi:10.1016/j.neucom.2019.04.087.
– start-page: 177
  year: 2010
  end-page: 186
  ident: b0140
  article-title: Large-scale machine learning with stochastic gradient descent
  publication-title: Proceeding of the 19th International Conference on Computational Statistics
– start-page: 315
  year: 2013
  end-page: 323
  ident: b0115
  article-title: Accelerating stochastic gradient descent using predictive variance reduction
  publication-title: Proceeding of the 27th Neural Information Processing Systems
– volume: 408
  start-page: 42
  year: 2020
  end-page: 50
  ident: b0105
  article-title: Convolutional neural networks with fractional order gradient method
  publication-title: Neurocomputing
– volume: 417
  start-page: 290
  year: 2020
  end-page: 301
  ident: b0085
  article-title: Impulsive effects on stability and passivity analysis of memristor-based fractional-order competitive neural networks
  publication-title: Neurocomputing
– volume: 11
  start-page: 137
  year: 2020
  end-page: 146
  ident: b0005
  article-title: Handwriting recognition using artificial intelligence neural network and image processing
  publication-title: International Journal of Advanced Computer Science and Applications
– volume: 19
  start-page: 263
  year: 2009
  end-page: 269
  ident: b0155
  article-title: Simple conditions for practical stability of positive fractional discrete-time linear systems
  publication-title: International Journal of Applied Mathematics and Computer Science
– volume: 12
  start-page: 2121
  year: 2011
  end-page: 2159
  ident: b0125
  article-title: Adaptive subgradient methods for online learning and stochastic optimization
  publication-title: Journal of Machine Learning Research
– volume: 1
  start-page: 541
  year: 1989
  end-page: 551
  ident: b0040
  article-title: Backpropagation applied to handwritten zip code recognition
  publication-title: Neural Computation
– volume: 12
  start-page: 145
  year: 1999
  end-page: 151
  ident: b0145
  article-title: On the momentum term in gradient descent learning algorithms
  publication-title: Neural Networks
– volume: 393
  start-page: 1
  year: 2020
  end-page: 14
  ident: b0035
  article-title: Deep face recognition with clustering based domain adaptation
  publication-title: Neurocomputing
– start-page: 1
  year: 2015
  end-page: 14
  ident: b0055
  article-title: deep convolutional networks for large scale image recognition
  publication-title: 2015 International Conference on Learning Representations (ICLR), San Diego, USA
– volume: 131
  start-page: 128
  year: 2020
  end-page: 134
  ident: b0010
  article-title: Facial expression recognition based on deep convolution long short-term memory networks of double-channel weighted mixture
  publication-title: Pattern Recognition Letters
– volume: 358
  start-page: 109
  year: 2019
  end-page: 118
  ident: b0015
  article-title: Recognition oriented facial image quality assessment via deep convolutional neural network
  publication-title: Neurocomputing
– volume: 11
  start-page: 137
  issue: 7
  year: 2020
  ident: 10.1016/j.neucom.2021.03.075_b0005
  article-title: Handwriting recognition using artificial intelligence neural network and image processing
  publication-title: International Journal of Advanced Computer Science and Applications
  doi: 10.14569/IJACSA.2020.0110719
– ident: 10.1016/j.neucom.2021.03.075_b0110
  doi: 10.1016/j.neucom.2019.04.087
– volume: 19
  start-page: 263
  issue: 2
  year: 2009
  ident: 10.1016/j.neucom.2021.03.075_b0155
  article-title: Simple conditions for practical stability of positive fractional discrete-time linear systems
  publication-title: International Journal of Applied Mathematics and Computer Science
  doi: 10.2478/v10006-009-0022-6
– volume: 12
  start-page: 2121
  year: 2011
  ident: 10.1016/j.neucom.2021.03.075_b0125
  article-title: Adaptive subgradient methods for online learning and stochastic optimization
  publication-title: Journal of Machine Learning Research
– volume: 365
  start-page: 191
  year: 2019
  ident: 10.1016/j.neucom.2021.03.075_b0025
  article-title: TA-CNN: two-way attention models in deep convolutional neural network for plant recognition
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2019.07.016
– start-page: 1899
  year: 2017
  ident: 10.1016/j.neucom.2021.03.075_b0120
  article-title: Nesterov’s accelerated gradient and momentum as approximations to regularised update descent
– volume: 408
  start-page: 42
  year: 2020
  ident: 10.1016/j.neucom.2021.03.075_b0105
  article-title: Convolutional neural networks with fractional order gradient method
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2019.10.017
– start-page: 1097
  year: 2012
  ident: 10.1016/j.neucom.2021.03.075_b0050
  article-title: classification with deep convolutional neural networks
– start-page: 1
  year: 2015
  ident: 10.1016/j.neucom.2021.03.075_b0055
  article-title: deep convolutional networks for large scale image recognition
– volume: 1
  start-page: 129
  issue: 16
  year: 2006
  ident: 10.1016/j.neucom.2021.03.075_b0150
  article-title: Fractional Kalman filter algorithm for the states, parameters and order of fractional system estimation
  publication-title: International Journal of Applied Mathematics and Computer Science
– start-page: 1
  year: 2015
  ident: 10.1016/j.neucom.2021.03.075_b0060
  article-title: Going deeper with convolutions
– volume: 358
  start-page: 109
  year: 2019
  ident: 10.1016/j.neucom.2021.03.075_b0015
  article-title: Recognition oriented facial image quality assessment via deep convolutional neural network
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2019.04.057
– volume: 12
  issue: 5
  year: 2020
  ident: 10.1016/j.neucom.2021.03.075_b0095
  article-title: A delay-dividing approach to robust stability of uncertain stochastic complex-valued hopfield delayed neural networks
  publication-title: Symmetry
  doi: 10.3390/sym12050683
– volume: 1
  start-page: 541
  issue: 4
  year: 1989
  ident: 10.1016/j.neucom.2021.03.075_b0040
  article-title: Backpropagation applied to handwritten zip code recognition
  publication-title: Neural Computation
  doi: 10.1162/neco.1989.1.4.541
– start-page: 913
  year: 2019
  ident: 10.1016/j.neucom.2021.03.075_b0075
  article-title: Optimize deep convolutional neural network with ternarized weights and high accuracy
– start-page: 1
  year: 2015
  ident: 10.1016/j.neucom.2021.03.075_b0130
  article-title: A method for stochastic optimization
– volume: 378
  start-page: 45
  year: 2020
  ident: 10.1016/j.neucom.2021.03.075_b0080
  article-title: Eye localization based on weight binarization cascade convolution neural network
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2019.10.048
– start-page: 177
  year: 2010
  ident: 10.1016/j.neucom.2021.03.075_b0140
  article-title: Large-scale machine learning with stochastic gradient descent
– volume: 55
  start-page: 424
  year: 2018
  ident: 10.1016/j.neucom.2021.03.075_b0070
  article-title: Feedback weight convolutional neural network for gait recognition
  publication-title: Journal of Visual Communication and Image Representation
  doi: 10.1016/j.jvcir.2018.06.019
– volume: 86
  start-page: 2278
  issue: 11
  year: 1998
  ident: 10.1016/j.neucom.2021.03.075_b0045
  article-title: Gradient-based learning applied to document recognition
  publication-title: Proceedings of the IEEE
  doi: 10.1109/5.726791
– volume: 346
  start-page: 531
  year: 2019
  ident: 10.1016/j.neucom.2021.03.075_b0135
  article-title: Representations of acting processes and memory effects: General fractional derivative and its application to theory of heat conduction with finite wave speeds
  publication-title: Applied Mathematics and Computation
  doi: 10.1016/j.amc.2018.10.037
– volume: 25
  start-page: 690
  issue: 4
  year: 2014
  ident: 10.1016/j.neucom.2021.03.075_b0100
  article-title: Lagrange stability of memristive neural networks with discrete and distributed delays
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
  doi: 10.1109/TNNLS.2013.2280458
– volume: 417
  start-page: 290
  year: 2020
  ident: 10.1016/j.neucom.2021.03.075_b0085
  article-title: Impulsive effects on stability and passivity analysis of memristor-based fractional-order competitive neural networks
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2020.07.036
– volume: 131
  start-page: 128
  year: 2020
  ident: 10.1016/j.neucom.2021.03.075_b0010
  article-title: Facial expression recognition based on deep convolution long short-term memory networks of double-channel weighted mixture
  publication-title: Pattern Recognition Letters
  doi: 10.1016/j.patrec.2019.12.013
– volume: 21
  start-page: 947
  issue: 3
  year: 2020
  ident: 10.1016/j.neucom.2021.03.075_b0030
  article-title: Defect detection of pantograph slide based on deep learning and image processing technology
  publication-title: IEEE Transactions on Intelligent Transportation Systems
  doi: 10.1109/TITS.2019.2900385
– volume: 168
  start-page: 1
  year: 2020
  ident: 10.1016/j.neucom.2021.03.075_b0020
  article-title: See the forest and the trees: effective machine and deep learning algorithms for wood filtering and tree species classification from terrestrial laser scanning
  publication-title: Isprs Journal of Photogrammetry and Remote Sensing
  doi: 10.1016/j.isprsjprs.2020.08.001
– volume: 237
  start-page: 332
  year: 2017
  ident: 10.1016/j.neucom.2021.03.075_b0065
  article-title: Choroid segmentation from optical coherence tomography with graph-edge weights learned from deep convolutional neural networks
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2017.01.023
– start-page: 315
  year: 2013
  ident: 10.1016/j.neucom.2021.03.075_b0115
  article-title: Accelerating stochastic gradient descent using predictive variance reduction
– volume: 393
  start-page: 1
  year: 2020
  ident: 10.1016/j.neucom.2021.03.075_b0035
  article-title: Deep face recognition with clustering based domain adaptation
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2020.02.005
– volume: 28
  start-page: 206
  issue: 1
  year: 2017
  ident: 10.1016/j.neucom.2021.03.075_b0090
  article-title: Global mittag-leffler stabilization of fractional-order memristive neural networks
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
  doi: 10.1109/TNNLS.2015.2506738
– volume: 12
  start-page: 145
  issue: 1
  year: 1999
  ident: 10.1016/j.neucom.2021.03.075_b0145
  article-title: On the momentum term in gradient descent learning algorithms
  publication-title: Neural Networks
  doi: 10.1016/S0893-6080(98)00116-6
SSID ssj0017129
Score 2.4358091
Snippet This paper proposes a parameter training method via the fractional-order momentum for convolutional neural networks (CNNs). To update the parameters of CNNs...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 85
SubjectTerms CIFAR-10
Convolutional neural networks
Fractional-order difference
MNIST
Momentum
Title Convolutional neural networks based on fractional-order momentum for parameter training
URI https://dx.doi.org/10.1016/j.neucom.2021.03.075
Volume 449
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Baden-Württemberg Complete Freedom Collection (Elsevier)
  customDbUrl:
  eissn: 1872-8286
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017129
  issn: 0925-2312
  databaseCode: GBLVA
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: Elsevier SD Complete Freedom Collection [SCCMFC]
  customDbUrl:
  eissn: 1872-8286
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017129
  issn: 0925-2312
  databaseCode: ACRLP
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals [SCFCJ]
  customDbUrl:
  eissn: 1872-8286
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017129
  issn: 0925-2312
  databaseCode: AIKHN
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: Science Direct
  customDbUrl:
  eissn: 1872-8286
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017129
  issn: 0925-2312
  databaseCode: .~1
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVLSH
  databaseName: Elsevier Journals
  customDbUrl:
  mediaType: online
  eissn: 1872-8286
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017129
  issn: 0925-2312
  databaseCode: AKRWK
  dateStart: 19930201
  isFulltext: true
  providerName: Library Specific Holdings
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LSwMxEA6lXrz4Fuuj5OB1bZNNs7vHUixVsRct9haymyxU2m2pW4_-dmey2aIgCp6WLDMQJsnMJHzzDSHXec5SG_UMnG8TBwJrdONQw9AajI6Qo7jWCY9jOZqI-2lv2iCDuhYGYZXe91c-3Xlr_6fjrdlZzWadp27C4RbFOEfSM8mQdluICLsY3HxsYR4sYrzi2-O9AKXr8jmH8SrsBjEjHAKdozpFtOFP4elLyBkekD2fK9J-NZ1D0rDFEdmv-zBQfyyPyctgWbz7LQTySFHpPg7g_UYxUBm6LGi-rqoY9DxwjJt0gfQL5WZBIXOlSAK-QHAMrdtGnJDJ8PZ5MAp8w4Qgg8y_DCLDcm2YzU2aGhGbSGprkA4yFFZYuAcnUZLlVneljngsWZrmMkGOxtBKBjrhKWkWy8KeESrAbNKAdNqTIssgDxcWljNJcst1bHWLhLWdVObZxHF2c1XDxl5VZV2F1lXdUIF1WyTYaq0qNo0_5KN6CdS3XaHA4f-qef5vzQuyiyN8N2bxJWmW6429gsSjTNtuZ7XJTv_uYTT-BLYl2w0
linkProvider Elsevier
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT8MwDI7GOMCFN2I8c-BatqRp0h7RxDRg24VN7Ba1TSqBtm4aG0d-O3baTiAhkDhVbW0pchLbiT5_JuQ6y1hiVWBgf5vQE1ijG_oxvFqD0RFyFNc6oT-Q3ZF4GAfjGmlXtTAIqyx9f-HTnbcuvzRLazbnLy_Np1bE4RTFOEfSM8nkBtkUAVd4Arv5WOM8mGK8INzjgYfiVf2cA3nldoWgEQ6RznGdItzwp_j0JeZ09shOmSzS22I8-6Rm8wOyWzVioOW-PCTP7Vn-Xq4hkEeOSvdwCO83ipHK0FlOs0VRxhBPPEe5SafIv7BcTSmkrhRZwKeIjqFV34gjMurcDdtdr-yY4KWQ-i89ZVgWG2YzkyRGhEbJ2Brkg_SFFRYOwpGK0szGLRkrHkqWJJmMkKTRt5KBjn9M6vkstyeECjCbNCCdBFKkKSTiwsJ8RlFmeRzauEH8yk46LenEcXQTXeHGXnVhXY3W1S1fg3UbxFtrzQs6jT_kVTUF-tuy0ODxf9U8_bfmFdnqDvs93bsfPJ6RbfyDl8gsPCf15WJlLyALWSaXbpV9AuV83KI
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=Convolutional+neural+networks+based+on+fractional-order+momentum+for+parameter+training&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Kan%2C+Tao&rft.au=Gao%2C+Zhe&rft.au=Yang%2C+Chuang&rft.au=Jian%2C+Jing&rft.date=2021-08-18&rft.pub=Elsevier+B.V&rft.issn=0925-2312&rft.eissn=1872-8286&rft.volume=449&rft.spage=85&rft.epage=99&rft_id=info:doi/10.1016%2Fj.neucom.2021.03.075&rft.externalDocID=S0925231221004616
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon