Convergence of a Gradient-Based Learning Algorithm With Penalty for Ridge Polynomial Neural Networks

Recently there have been renewed interests in high order neural networks (HONNs) for its powerful mapping capability. Ridge polynomial neural network (RPNN) is an important kind of HONNs, which always occupies a key position as an efficient instrument in the tasks of classification or regression. In...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE access Ročník 9; s. 28742 - 28752
Hlavní autoři: Fan, Qinwei, Peng, Jigen, Li, Haiyang, Lin, Shoujin
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:2169-3536, 2169-3536
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Recently there have been renewed interests in high order neural networks (HONNs) for its powerful mapping capability. Ridge polynomial neural network (RPNN) is an important kind of HONNs, which always occupies a key position as an efficient instrument in the tasks of classification or regression. In order to make the convergence speed faster and the network generalization ability stronger, we introduce a regularization model for RPNN with Group Lasso penalty, which deals with the structural sparse problem at the group level in this paper. Nevertheless, there are two main obstacles for introducing the Group Lasso penalty, one is numerical oscillation and the other is convergence analysis challenge. In doing so, we adopt smoothing function to approximate the Group Lasso penalty to overcome these drawbacks. Meanwhile, strong and weak convergence theorems, and monotonicity theorems are provided for this novel algorithm. We also demonstrate the efficiency of our proposed algorithm by numerical experiments, and compare it to the no regularizer, <inline-formula> <tex-math notation="LaTeX">L_{2} </tex-math></inline-formula> regularizer, <inline-formula> <tex-math notation="LaTeX">L_{1/2} </tex-math></inline-formula> regularizer, smoothing <inline-formula> <tex-math notation="LaTeX">L_{1/2} </tex-math></inline-formula> regularizer, and the Group Lasso regularizer, and also the relevant theoretical analysis has been verified.
AbstractList Recently there have been renewed interests in high order neural networks (HONNs) for its powerful mapping capability. Ridge polynomial neural network (RPNN) is an important kind of HONNs, which always occupies a key position as an efficient instrument in the tasks of classification or regression. In order to make the convergence speed faster and the network generalization ability stronger, we introduce a regularization model for RPNN with Group Lasso penalty, which deals with the structural sparse problem at the group level in this paper. Nevertheless, there are two main obstacles for introducing the Group Lasso penalty, one is numerical oscillation and the other is convergence analysis challenge. In doing so, we adopt smoothing function to approximate the Group Lasso penalty to overcome these drawbacks. Meanwhile, strong and weak convergence theorems, and monotonicity theorems are provided for this novel algorithm. We also demonstrate the efficiency of our proposed algorithm by numerical experiments, and compare it to the no regularizer, <tex-math notation="LaTeX">$L_{2}$ </tex-math> regularizer, <tex-math notation="LaTeX">$L_{1/2}$ </tex-math> regularizer, smoothing <tex-math notation="LaTeX">$L_{1/2}$ </tex-math> regularizer, and the Group Lasso regularizer, and also the relevant theoretical analysis has been verified.
Recently there have been renewed interests in high order neural networks (HONNs) for its powerful mapping capability. Ridge polynomial neural network (RPNN) is an important kind of HONNs, which always occupies a key position as an efficient instrument in the tasks of classification or regression. In order to make the convergence speed faster and the network generalization ability stronger, we introduce a regularization model for RPNN with Group Lasso penalty, which deals with the structural sparse problem at the group level in this paper. Nevertheless, there are two main obstacles for introducing the Group Lasso penalty, one is numerical oscillation and the other is convergence analysis challenge. In doing so, we adopt smoothing function to approximate the Group Lasso penalty to overcome these drawbacks. Meanwhile, strong and weak convergence theorems, and monotonicity theorems are provided for this novel algorithm. We also demonstrate the efficiency of our proposed algorithm by numerical experiments, and compare it to the no regularizer, [Formula Omitted] regularizer, [Formula Omitted] regularizer, smoothing [Formula Omitted] regularizer, and the Group Lasso regularizer, and also the relevant theoretical analysis has been verified.
Recently there have been renewed interests in high order neural networks (HONNs) for its powerful mapping capability. Ridge polynomial neural network (RPNN) is an important kind of HONNs, which always occupies a key position as an efficient instrument in the tasks of classification or regression. In order to make the convergence speed faster and the network generalization ability stronger, we introduce a regularization model for RPNN with Group Lasso penalty, which deals with the structural sparse problem at the group level in this paper. Nevertheless, there are two main obstacles for introducing the Group Lasso penalty, one is numerical oscillation and the other is convergence analysis challenge. In doing so, we adopt smoothing function to approximate the Group Lasso penalty to overcome these drawbacks. Meanwhile, strong and weak convergence theorems, and monotonicity theorems are provided for this novel algorithm. We also demonstrate the efficiency of our proposed algorithm by numerical experiments, and compare it to the no regularizer, <inline-formula> <tex-math notation="LaTeX">L_{2} </tex-math></inline-formula> regularizer, <inline-formula> <tex-math notation="LaTeX">L_{1/2} </tex-math></inline-formula> regularizer, smoothing <inline-formula> <tex-math notation="LaTeX">L_{1/2} </tex-math></inline-formula> regularizer, and the Group Lasso regularizer, and also the relevant theoretical analysis has been verified.
Author Li, Haiyang
Peng, Jigen
Lin, Shoujin
Fan, Qinwei
Author_xml – sequence: 1
  givenname: Qinwei
  orcidid: 0000-0002-1017-3496
  surname: Fan
  fullname: Fan, Qinwei
  organization: School of Mathematics and Information Science, Guangzhou University, Guangzhou, China
– sequence: 2
  givenname: Jigen
  orcidid: 0000-0002-7207-3183
  surname: Peng
  fullname: Peng, Jigen
  email: jgpeng@gzhu.edu.cn
  organization: School of Mathematics and Information Science, Guangzhou University, Guangzhou, China
– sequence: 3
  givenname: Haiyang
  orcidid: 0000-0001-7238-2456
  surname: Li
  fullname: Li, Haiyang
  organization: School of Mathematics and Information Science, Guangzhou University, Guangzhou, China
– sequence: 4
  givenname: Shoujin
  surname: Lin
  fullname: Lin, Shoujin
  organization: School of Mathematics and Information Science, Guangzhou University, Guangzhou, China
BookMark eNp9kU9v1DAQxSNUJErpJ-jFEucs_rtxjktUSqUVVLQSR2tij4OXrF0cb9F-e9KmIMSBOcxYT_N7tvVeVycxRayqC0ZXjNH23abrLm9vV5xyuhJUai7Ui-qUs3VbCyXWJ3-dX1Xn07Sjc-lZUs1p5boUHzAPGC2S5AmQqwwuYCz1e5jQkS1CjiEOZDMOKYfybU--zp3cYISxHIlPmXwJbkByk8ZjTPsAI_mEh_w0ys-Uv09vqpcexgnPn-dZdffh8q77WG8_X113m21tJdWl5koiUxZsr4TtsW-x5aAVets4K6xUWlkPTHpvpaVoGdeONY1ALTRoKc6q68XWJdiZ-xz2kI8mQTBPQsqDgVyCHdE4qp2G3iPlQur5osZJRQUwtWZcNv3s9Xbxus_pxwGnYnbpkOcvT4bLlmulWqXnrXbZsjlNU0ZvbChQQoolQxgNo-YxIrNEZB4jMs8Rzaz4h_394v9TFwsVEPEP0QrGWEPFLzynnxw
CODEN IAECCG
CitedBy_id crossref_primary_10_1002_adts_202200047
crossref_primary_10_1007_s11063_022_10956_w
crossref_primary_10_1186_s12302_025_01078_w
crossref_primary_10_3390_electronics13081585
crossref_primary_10_1007_s13042_023_01901_x
crossref_primary_10_1080_02331934_2022_2057852
crossref_primary_10_1007_s11063_022_11069_0
Cites_doi 10.1016/j.asoc.2017.07.059
10.1109/72.377967
10.1016/j.neucom.2014.09.031
10.1016/j.neucom.2012.05.022
10.1109/CCMB.2013.6609169
10.1007/11893028_63
10.1016/j.neucom.2013.10.023
10.1016/j.neucom.2013.09.015
10.1371/journal.pone.0167248
10.1109/ACCESS.2017.2713389
10.1016/S0261-5177(99)00067-9
10.1109/TCYB.2019.2950105
10.1016/j.neunet.2010.09.007
10.1016/j.neucom.2017.08.037
10.1109/72.839013
10.1007/s00521-014-1730-x
10.1023/A:1022967523886
10.1364/AO.26.004972
10.1109/72.80236
10.1109/ACCESS.2020.3031647
10.1016/j.ins.2019.10.048
10.1016/j.neucom.2004.05.004
10.1162/neco.2007.19.12.3356
10.1111/j.1467-9868.2005.00532.x
10.7763/IJCEE.2011.V3.288
10.1016/j.eswa.2010.09.037
10.1007/s11356-016-7149-4
10.1109/TSMC.2015.2406855
10.1016/j.neucom.2008.12.005
10.1016/j.neucom.2007.12.004
10.1109/VIPMC.2003.1220516
10.1016/j.neunet.2013.11.006
10.1111/j.1467-9868.2007.00627.x
10.1080/10618600.2012.681250
10.9781/ijimai.2019.04.004
10.1109/TSMC.1971.4308320
10.1109/IJCNN.1991.155142
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID 97E
ESBDL
RIA
RIE
AAYXX
CITATION
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
DOA
DOI 10.1109/ACCESS.2020.3048235
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE Xplore Open Access Journals
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE/IET Electronic Library
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
METADEX
Technology Research Database
Materials Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DOAJ Open Access Full Text
DatabaseTitle CrossRef
Materials Research Database
Engineered Materials Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
METADEX
Computer and Information Systems Abstracts Professional
DatabaseTitleList
Materials Research Database

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Open Access Full Text
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2169-3536
EndPage 28752
ExternalDocumentID oai_doaj_org_article_d08d8abfe023489e97d4503a1561247b
10_1109_ACCESS_2020_3048235
9311170
Genre orig-research
GrantInformation_xml – fundername: 65th China Postdoctoral Science Foundation
  grantid: 2019M652837
  funderid: 10.13039/501100002858
– fundername: National Science Foundation of China
  grantid: 11771347
  funderid: 10.13039/501100001809
GroupedDBID 0R~
4.4
5VS
6IK
97E
AAJGR
ABAZT
ABVLG
ACGFS
ADBBV
AGSQL
ALMA_UNASSIGNED_HOLDINGS
BCNDV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
ESBDL
GROUPED_DOAJ
IPLJI
JAVBF
KQ8
M43
M~E
O9-
OCL
OK1
RIA
RIE
RNS
AAYXX
CITATION
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c408t-254e15cacb53cbeb9e92a85efc7dc3c4585cfa14ffc4c0ec128d1773e838a843
IEDL.DBID DOA
ISICitedReferencesCount 10
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000621394200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2169-3536
IngestDate Fri Oct 03 12:32:20 EDT 2025
Mon Jun 30 06:10:27 EDT 2025
Sat Nov 29 06:11:49 EST 2025
Tue Nov 18 22:22:55 EST 2025
Wed Aug 27 02:29:14 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License https://creativecommons.org/licenses/by-nc-nd/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c408t-254e15cacb53cbeb9e92a85efc7dc3c4585cfa14ffc4c0ec128d1773e838a843
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-1017-3496
0000-0001-7238-2456
0000-0002-7207-3183
OpenAccessLink https://doaj.org/article/d08d8abfe023489e97d4503a1561247b
PQID 2492855958
PQPubID 4845423
PageCount 11
ParticipantIDs crossref_primary_10_1109_ACCESS_2020_3048235
ieee_primary_9311170
doaj_primary_oai_doaj_org_article_d08d8abfe023489e97d4503a1561247b
crossref_citationtrail_10_1109_ACCESS_2020_3048235
proquest_journals_2492855958
PublicationCentury 2000
PublicationDate 20210000
2021-00-00
20210101
2021-01-01
PublicationDateYYYYMMDD 2021-01-01
PublicationDate_xml – year: 2021
  text: 20210000
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE access
PublicationTitleAbbrev Access
PublicationYear 2021
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref34
ref12
ref37
ref15
ref36
ref14
ref31
ref30
han (ref24) 2016; 56
ref33
ref11
ref32
ref10
ref2
ref1
ref39
ref16
ref19
ref18
wu (ref22) 2005
yuan (ref44) 1997
ref23
wu (ref17) 2007; 14
ref26
sharma (ref28) 2010; 12
ref25
ref20
ref42
ref41
ref21
ref43
fan (ref38) 2020; 2020
ref27
ref29
ref8
bishop (ref35) 2006
ref7
ref9
ref4
ref3
ref6
ref5
ref40
References_xml – volume: 2020
  start-page: 1
  year: 2020
  ident: ref38
  article-title: Smoothing L? regularization for extreme learning machine
  publication-title: Math Problems Eng
– ident: ref14
  doi: 10.1016/j.asoc.2017.07.059
– ident: ref5
  doi: 10.1109/72.377967
– ident: ref19
  doi: 10.1016/j.neucom.2014.09.031
– ident: ref34
  doi: 10.1016/j.neucom.2012.05.022
– ident: ref32
  doi: 10.1109/CCMB.2013.6609169
– ident: ref36
  doi: 10.1007/11893028_63
– ident: ref27
  doi: 10.1016/j.neucom.2013.10.023
– volume: 14
  start-page: 95
  year: 2007
  ident: ref17
  article-title: Convergence of asynchronous batch gradient method for pi-sigma neural networks
  publication-title: Dyna Continuous Discrete Impul Syst
– ident: ref8
  doi: 10.1016/j.neucom.2013.09.015
– year: 1997
  ident: ref44
  publication-title: Optimization Theory and Methods
– ident: ref9
  doi: 10.1371/journal.pone.0167248
– start-page: 288
  year: 2005
  ident: ref22
  article-title: Improving generalization performance of artificial neural networks with genetic algorithms
  publication-title: Proc IEEE Int Conf Granular Comput
– ident: ref33
  doi: 10.1109/ACCESS.2017.2713389
– ident: ref20
  doi: 10.1016/S0261-5177(99)00067-9
– volume: 12
  start-page: 7847
  year: 2010
  ident: ref28
  article-title: Constructive neural networks: A review
  publication-title: Int J Eng Sci Technol
– ident: ref39
  doi: 10.1109/TCYB.2019.2950105
– ident: ref16
  doi: 10.1016/j.neunet.2010.09.007
– ident: ref15
  doi: 10.1016/j.neucom.2017.08.037
– ident: ref30
  doi: 10.1109/72.839013
– ident: ref37
  doi: 10.1007/s00521-014-1730-x
– volume: 56
  start-page: 3
  year: 2016
  ident: ref24
  article-title: Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding
  publication-title: FIBER
– ident: ref6
  doi: 10.1023/A:1022967523886
– ident: ref3
  doi: 10.1364/AO.26.004972
– ident: ref23
  doi: 10.1109/72.80236
– ident: ref40
  doi: 10.1109/ACCESS.2020.3031647
– ident: ref26
  doi: 10.1016/j.ins.2019.10.048
– ident: ref7
  doi: 10.1016/j.neucom.2004.05.004
– ident: ref31
  doi: 10.1162/neco.2007.19.12.3356
– ident: ref42
  doi: 10.1111/j.1467-9868.2005.00532.x
– ident: ref29
  doi: 10.7763/IJCEE.2011.V3.288
– ident: ref1
  doi: 10.1016/j.eswa.2010.09.037
– ident: ref21
  doi: 10.1007/s11356-016-7149-4
– year: 2006
  ident: ref35
  publication-title: Pattern Recognition and Machine Learning
– ident: ref13
  doi: 10.1109/TSMC.2015.2406855
– ident: ref11
  doi: 10.1016/j.neucom.2008.12.005
– ident: ref18
  doi: 10.1016/j.neucom.2007.12.004
– ident: ref12
  doi: 10.1109/VIPMC.2003.1220516
– ident: ref25
  doi: 10.1016/j.neunet.2013.11.006
– ident: ref43
  doi: 10.1111/j.1467-9868.2007.00627.x
– ident: ref41
  doi: 10.1080/10618600.2012.681250
– ident: ref10
  doi: 10.9781/ijimai.2019.04.004
– ident: ref2
  doi: 10.1109/TSMC.1971.4308320
– ident: ref4
  doi: 10.1109/IJCNN.1991.155142
SSID ssj0000816957
Score 2.2912338
Snippet Recently there have been renewed interests in high order neural networks (HONNs) for its powerful mapping capability. Ridge polynomial neural network (RPNN) is...
SourceID doaj
proquest
crossref
ieee
SourceType Open Website
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 28742
SubjectTerms Algorithms
Biological neural networks
Convergence
high order neural networks
Input variables
Machine learning
Neural networks
Polynomials
Regression analysis
Regularization
ridge polynomial neural network
Smoothing
smoothing Group Lasso
Smoothing methods
Theorems
Training
SummonAdditionalLinks – databaseName: IEEE/IET Electronic Library
  dbid: RIE
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3BbtQwELXaigMcoKUgFtrKB44NdWJnbR-3KwqnaoUq0ZvljMel0rKpdlOk_j1jrxuQQEhckiiyHdvPyXgmM28Yey_bSEISp1WLyVo1raHyUoSqU1Z22ABYL3KyCX15aa6v7WKHnY6xMIiYnc_wQ7rM__JDD_fJVHZmZZ0SpeyyXa2n21it0Z6SEkjYVhdioVrYs9l8TmMgFbAhzZQWapNTuv0SPpmjvyRV-eNLnMXLxYv_69g-e162kXy2xf2A7eDqJXv2G7ngIQvz5FCeYyuR95F7_mmd_buG6pxEV-CFWvWGz5Y3_fp2-Padf6UjXyA1PTxw2s7yLymciy_65UMKX6YnJjKPfMre45tX7Ori49X8c1VyKlSghBkq0gexbsFD10rosLNoG29ajKADSFCkPUD0tYoRFAgEEl-h1lqikcYbJV-zvVW_wjeMK5pYaKglESNJQp143gn5KVphAmg9Yc3jXDsofOMp7cXSZb1DWLcFyCWAXAFowk7HSndbuo1_Fz9PII5FE1d2vkHouPLquUD9Mb6LSNsTZWjAOqhWSF-nxKBKdxN2mBAdGylgTtjR45Jw5b3euMSvaEgJa83bv9d6x542yeslG2mO2N6wvsdj9gR-DLeb9Ulesj8B8BPpdw
  priority: 102
  providerName: IEEE
Title Convergence of a Gradient-Based Learning Algorithm With Penalty for Ridge Polynomial Neural Networks
URI https://ieeexplore.ieee.org/document/9311170
https://www.proquest.com/docview/2492855958
https://doaj.org/article/d08d8abfe023489e97d4503a1561247b
Volume 9
WOSCitedRecordID wos000621394200001&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: PRVAON
  databaseName: DOAJ Open Access Full Text
  customDbUrl:
  eissn: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: DOA
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1NT9wwELUqxKEcKiggli_50GMjnNhZ28dlBe2laFUhlZvlTGxA2u6i3YDEhd_OjGO2KyG1l14cKXLsZGbi8Vgz7zH2RdYRnWQYFnWg06phCYWXoi0aZWUTKgDrRSKb0FdX5ubGTtaovignrIcH7gV31grTGt_EgM5FGRusblUtpC-J1lHphlZfoe1aMJXWYFMOba0zzFAp7NloPMYvwoCwwjgVzbZKBG9_XFFC7M8UK-_W5eRsLrfZp7xL5KP-7XbYhzD7zLbWsAN3WTumfPFUOhn4PHLPvy1S-lZXnKNnanlGTr3lo-ntfHHf3f3mv7Dlk4BDd88cd6v8J1Vr8cl8-kzVyTgjYXWkS0oOX-6x68uL6_H3IlMmFKCE6QoM90JZg4emltCEBuVVeVOHCLoFCQqDA4i-VDGCAhEAvVNbai2DkcYbJffZxmw-CweMK5QUVDiSiBEdnSYYd1TsMFhUCGg9YNWb8BxkOHFitZi6FFYI63qJO5K4yxIfsK-rhx56NI2_dz8nray6EhR2uoEG4rKBuH8ZyIDtkk5Xg1hZEtvOgB2_6djl33bpCD7RYIxVm8P_MfUR-1hRCkw6sTlmG93iMZywTXjq7peL02Sx2P54uThNdYeveX7uCw
linkProvider Directory of Open Access Journals
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fb9MwED6NgQQ88GsgCgP8wOPCnNip7ceuYgwxqgpVYm9Wcrlsk0qD2gxp_z1n1wtIICRekiiyHdufk_Nd7r4DeKvKloUkjbOSgrVqnGNWKdlktXaqpgLRVTImmzCzmT07c_MdOBhiYYgoOp_Ru3AZ_-U3HV4FU9mhU3lIlHILbpea9Z5ttNZgUQkpJFxpErVQLt3hZDrlUbASWLBuyku1iEndfomfyNKf0qr88S2OAub44f917RE8SBtJMdki_xh2aPUE7v9GL7gHzTS4lMfoShJdKyrxYR09vPrsiIVXIxK56rmYLM-79WV_8U185aOYEzfdXwve0IovIaBLzLvldQhg5icGOo94iv7jm6ewOH6_mJ5kKatChlraPmONkPISK6xLhTXVjlxR2ZJaNA0q1Kw_YFvlum1RoyRkAdbkxiiyylZWq2ewu-pW9ByE5onFgluSbcuy0ASmd8Z-TE7aBo0ZQXEz1x4T43hIfLH0UfOQzm8B8gEgnwAawcFQ6fuWcOPfxY8CiEPRwJYdbzA6Pr18vuH-2KpuiTco2vKATaNLqao8pAbVph7BXkB0aCSBOYL9myXh05u98YFh0bIaVtoXf6_1Bu6eLD6f-tOPs08v4V4RfGCiyWYfdvv1Fb2CO_ijv9ysX8fl-xM33-y-
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=Convergence+of+a+Gradient-Based+Learning+Algorithm+With+Penalty+for+Ridge+Polynomial+Neural+Networks&rft.jtitle=IEEE+access&rft.au=Fan%2C+Qinwei&rft.au=Peng%2C+Jigen&rft.au=Li%2C+Haiyang&rft.au=Lin%2C+Shoujin&rft.date=2021&rft.issn=2169-3536&rft.eissn=2169-3536&rft.volume=9&rft.spage=28742&rft.epage=28752&rft_id=info:doi/10.1109%2FACCESS.2020.3048235&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_ACCESS_2020_3048235
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon