A Training Algorithm for Locally Recurrent Neural Networks Based on the Explicit Gradient of the Loss Function

In this paper, a new algorithm for the training of Locally Recurrent Neural Networks (LRNNs) is presented, which aims to reduce computational complexity and at the same time guarantee the stability of the network during the training. The main feature of the proposed algorithm is the capability to re...

Full description

Saved in:
Bibliographic Details
Published inAlgorithms Vol. 18; no. 2; p. 104
Main Authors Carcangiu, Sara, Montisci, Augusto
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.02.2025
Subjects
Online AccessGet full text
ISSN1999-4893
1999-4893
DOI10.3390/a18020104

Cover

Abstract In this paper, a new algorithm for the training of Locally Recurrent Neural Networks (LRNNs) is presented, which aims to reduce computational complexity and at the same time guarantee the stability of the network during the training. The main feature of the proposed algorithm is the capability to represent the gradient of the error in an explicit form. The algorithm builds on the interpretation of Fibonacci’s sequence as the output of an IIR second-order filter, which makes it possible to use Binet’s formula that allows the generic terms of the sequence to be calculated directly. Thanks to this approach, the gradient of the loss function during the training can be explicitly calculated, and it can be expressed in terms of the parameters, which control the stability of the neural network.
AbstractList In this paper, a new algorithm for the training of Locally Recurrent Neural Networks (LRNNs) is presented, which aims to reduce computational complexity and at the same time guarantee the stability of the network during the training. The main feature of the proposed algorithm is the capability to represent the gradient of the error in an explicit form. The algorithm builds on the interpretation of Fibonacci’s sequence as the output of an IIR second-order filter, which makes it possible to use Binet’s formula that allows the generic terms of the sequence to be calculated directly. Thanks to this approach, the gradient of the loss function during the training can be explicitly calculated, and it can be expressed in terms of the parameters, which control the stability of the neural network.
Audience Academic
Author Montisci, Augusto
Carcangiu, Sara
Author_xml – sequence: 1
  givenname: Sara
  orcidid: 0000-0002-0270-6432
  surname: Carcangiu
  fullname: Carcangiu, Sara
– sequence: 2
  givenname: Augusto
  orcidid: 0000-0003-0008-2985
  surname: Montisci
  fullname: Montisci, Augusto
BookMark eNp9kVFrFDEQx4NUsK0--A0CPilcm2w2u8njWdpaOBSkPofZ7OSacy85kyz1vr1pT1oFkcBMmPzmz-Q_J-QoxICEvOXsTAjNzoEr1jDO2hfkmGutF63S4uiP-ytykvOGsU7qjh-TsKS3CXzwYU2X0zomX-621MVEV9HCNO3pV7RzShgK_Yxzgqmmch_T90w_QsaRxkDLHdLLn7vJW1_odYLRP-DRPT6sYs70ag62-Bhek5cOpoxvfudT8u3q8vbi02L15frmYrlaWKFkWaCEHiQT3DWqHRl3Cp0dJdbYAmgpGCoUUolBMiuFlq5BHJoORtHC2PfilNwcdMcIG7NLfgtpbyJ481iIaW0gFW8nNMgROtFXaYdtIwct2q5qCrQNDHxoqtaHg9YcdrC_r6Y8CXJmHlw3T65X-N0B3qX4Y8ZczCbOKdS_GsF7pmTbqe6ZWkOdwAcXSwK79dmapWqU1p2SulJn_6DqGXHrbd2787X-V8P7Q4NN1fSE7j-D_gIe6avt
Cites_doi 10.1109/5.58337
10.1162/neco.1992.4.2.141
10.54364/AAIML.2024.41120
10.1109/82.861421
10.1016/j.neunet.2017.03.002
10.1207/s15516709cog1402_1
10.1155/2020/4281219
10.1109/PROC.1975.10036
10.1016/S0166-4115(97)80111-2
10.1007/BFb0053992
10.1162/neco.1993.5.2.165
10.1515/zna-1980-0308
10.1162/neco.1989.1.1.39
10.1109/ICCCE.2010.5556806
10.1016/0893-6080(88)90021-4
10.1162/neco.1991.3.3.375
10.1109/TMTT.2005.845723
10.1038/s42254-023-00595-y
10.1109/TPAMI.2021.3117837
10.1109/TCSI.2004.841574
10.1109/IWCFTA.2010.60
ContentType Journal Article
Copyright COPYRIGHT 2025 MDPI AG
2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: COPYRIGHT 2025 MDPI AG
– notice: 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID AAYXX
CITATION
3V.
7SC
7TB
7XB
8AL
8FD
8FE
8FG
8FK
ABJCF
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
FR3
GNUQQ
HCIFZ
JQ2
K7-
KR7
L6V
L7M
L~C
L~D
M0N
M7S
P62
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
Q9U
ADTOC
UNPAY
DOA
DOI 10.3390/a18020104
DatabaseName CrossRef
ProQuest Central (Corporate)
Computer and Information Systems Abstracts
Mechanical & Transportation Engineering Abstracts
ProQuest Central (purchase pre-March 2016)
Computing Database (Alumni Edition)
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Materials Science & Engineering
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials
ProQuest Central
Technology Collection (via ProQuest SciTech Premium Collection)
ProQuest One Community College
ProQuest Central
Engineering Research Database
ProQuest Central Student
SciTech Premium Collection (Proquest)
ProQuest Computer Science Collection
Computer Science Database (Proquest)
Civil Engineering Abstracts
ProQuest Engineering Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Computing Database
Engineering Database (Proquest)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic
ProQuest Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic
ProQuest One Academic UKI Edition
ProQuest Central China
Engineering Collection
ProQuest Central Basic
Unpaywall for CDI: Periodical Content
Unpaywall
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Publicly Available Content Database
Computer Science Database
ProQuest Central Student
Technology Collection
Technology Research Database
Computer and Information Systems Abstracts – Academic
ProQuest One Academic Middle East (New)
Mechanical & Transportation Engineering Abstracts
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Engineering Collection
ProQuest Central Korea
ProQuest Central (New)
Advanced Technologies Database with Aerospace
Engineering Collection
Advanced Technologies & Aerospace Collection
Civil Engineering Abstracts
ProQuest Computing
Engineering Database
ProQuest Central Basic
ProQuest Computing (Alumni Edition)
ProQuest One Academic Eastern Edition
ProQuest Technology Collection
ProQuest SciTech Collection
Computer and Information Systems Abstracts Professional
ProQuest One Academic UKI Edition
Materials Science & Engineering Collection
Engineering Research Database
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
DatabaseTitleList Publicly Available Content Database

CrossRef

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
– sequence: 3
  dbid: 8FG
  name: ProQuest Technology Collection
  url: https://search.proquest.com/technologycollection1
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1999-4893
ExternalDocumentID oai_doaj_org_article_e1ea637efcfe425b9346c533ec2ab1b2
10.3390/a18020104
A828996859
10_3390_a18020104
GeographicLocations South Carolina
GeographicLocations_xml – name: South Carolina
GroupedDBID 23M
2WC
5VS
8FE
8FG
AADQD
AAFWJ
AAYXX
ABDBF
ABJCF
ABUWG
ACUHS
ADBBV
AFKRA
AFPKN
AFZYC
ALMA_UNASSIGNED_HOLDINGS
AMVHM
ARAPS
AZQEC
BCNDV
BENPR
BGLVJ
BPHCQ
CCPQU
CITATION
DWQXO
E3Z
ESX
GNUQQ
GROUPED_DOAJ
HCIFZ
IAO
ICD
ITC
J9A
K6V
K7-
KQ8
L6V
M7S
MODMG
M~E
OK1
OVT
P2P
PHGZM
PHGZT
PIMPY
PQGLB
PQQKQ
PROAC
PTHSS
TR2
TUS
3V.
7SC
7TB
7XB
8AL
8FD
8FK
FR3
JQ2
KR7
L7M
L~C
L~D
M0N
P62
PKEHL
PQEST
PQUKI
PRINS
Q9U
ADTOC
C1A
IPNFZ
RIG
UNPAY
ID FETCH-LOGICAL-c385t-e5a7a5031f284d01f8efcd5eefc4aa9530e8e3583b50c5395f2eeb26ad34ad773
IEDL.DBID UNPAY
ISSN 1999-4893
IngestDate Tue Oct 14 18:59:59 EDT 2025
Sun Oct 26 03:33:29 EDT 2025
Fri Jul 25 11:57:39 EDT 2025
Mon Oct 20 22:45:15 EDT 2025
Mon Oct 20 16:56:17 EDT 2025
Thu Oct 16 04:39:17 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
License cc-by
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c385t-e5a7a5031f284d01f8efcd5eefc4aa9530e8e3583b50c5395f2eeb26ad34ad773
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-0270-6432
0000-0003-0008-2985
OpenAccessLink https://proxy.k.utb.cz/login?url=https://doi.org/10.3390/a18020104
PQID 3170854686
PQPubID 2032439
ParticipantIDs doaj_primary_oai_doaj_org_article_e1ea637efcfe425b9346c533ec2ab1b2
unpaywall_primary_10_3390_a18020104
proquest_journals_3170854686
gale_infotracmisc_A828996859
gale_infotracacademiconefile_A828996859
crossref_primary_10_3390_a18020104
PublicationCentury 2000
PublicationDate 2025-02-01
PublicationDateYYYYMMDD 2025-02-01
PublicationDate_xml – month: 02
  year: 2025
  text: 2025-02-01
  day: 01
PublicationDecade 2020
PublicationPlace Basel
PublicationPlace_xml – name: Basel
PublicationTitle Algorithms
PublicationYear 2025
Publisher MDPI AG
Publisher_xml – name: MDPI AG
References Huang (ref_5) 2017; 90
Nerrand (ref_6) 1993; 5
Han (ref_1) 2022; 44
Cao (ref_4) 2005; 52
Widrow (ref_10) 1975; 63
Willamowski (ref_24) 1980; 35
Campolucci (ref_17) 2000; 47
ref_19
Pedro (ref_11) 2005; 53
ref_16
ref_25
Carcangiu (ref_26) 2020; 2020
Waibel (ref_2) 1989; 1
Elman (ref_14) 1990; 14
Grossberg (ref_8) 1988; 1
ref_22
ref_21
ref_20
Donahoe (ref_13) 1997; Volume 121
ref_3
Werbos (ref_18) 1990; 78
ref_28
ref_27
ref_9
Krotov (ref_12) 2023; 5
Battiti (ref_23) 1992; 4
Back (ref_15) 1991; 3
ref_7
References_xml – ident: ref_28
– ident: ref_9
– volume: 78
  start-page: 1550
  year: 1990
  ident: ref_18
  article-title: Backpropagation through time: What it does and how to do it
  publication-title: Proc. IEEE
  doi: 10.1109/5.58337
– ident: ref_3
– volume: 4
  start-page: 141
  year: 1992
  ident: ref_23
  article-title: First- and Second-Order Methods for Learning: Between Steepest Descent and Newton’s Method
  publication-title: Neural Comput.
  doi: 10.1162/neco.1992.4.2.141
– ident: ref_21
  doi: 10.54364/AAIML.2024.41120
– volume: 47
  start-page: 797
  year: 2000
  ident: ref_17
  article-title: Intrinsic stability-control method for recursive filters and neural networks
  publication-title: IEEE Trans. Circuits Syst. II Analog Digit. Signal Process.
  doi: 10.1109/82.861421
– volume: 90
  start-page: 21
  year: 2017
  ident: ref_5
  article-title: A time-delay neural network for solving time-dependent shortest path problem
  publication-title: Neural Netw.
  doi: 10.1016/j.neunet.2017.03.002
– volume: 14
  start-page: 179
  year: 1990
  ident: ref_14
  article-title: Finding Structure in Time
  publication-title: Cogn. Sci.
  doi: 10.1207/s15516709cog1402_1
– volume: 2020
  start-page: 4281219
  year: 2020
  ident: ref_26
  article-title: Forecasting-Aided Monitoring for the Distribution System State Estimation
  publication-title: Complexity
  doi: 10.1155/2020/4281219
– volume: 63
  start-page: 1692
  year: 1975
  ident: ref_10
  article-title: Adaptive noise cancelling: Principles and applications
  publication-title: Proc. IEEE
  doi: 10.1109/PROC.1975.10036
– volume: Volume 121
  start-page: 471
  year: 1997
  ident: ref_13
  article-title: Chapter 25—Serial Order: A Parallel Distributed Processing Approach
  publication-title: Advances in Psychology
  doi: 10.1016/S0166-4115(97)80111-2
– ident: ref_16
  doi: 10.1007/BFb0053992
– volume: 5
  start-page: 165
  year: 1993
  ident: ref_6
  article-title: Neural Networks and Nonlinear Adaptive Filtering: Unifying Concepts and New Algorithms
  publication-title: Neural Comput.
  doi: 10.1162/neco.1993.5.2.165
– volume: 35
  start-page: 317
  year: 1980
  ident: ref_24
  article-title: Irregular Oscillations in a Realistic Abstract Quadratic Mass Action System
  publication-title: Z. Für Naturforschung A
  doi: 10.1515/zna-1980-0308
– volume: 1
  start-page: 39
  year: 1989
  ident: ref_2
  article-title: Modular Construction of Time-Delay Neural Networks for Speech Recognition
  publication-title: Neural Comput.
  doi: 10.1162/neco.1989.1.1.39
– ident: ref_7
  doi: 10.1109/ICCCE.2010.5556806
– volume: 1
  start-page: 17
  year: 1988
  ident: ref_8
  article-title: Nonlinear neural networks: Principles, mechanisms, and architectures
  publication-title: Neural Netw.
  doi: 10.1016/0893-6080(88)90021-4
– volume: 3
  start-page: 375
  year: 1991
  ident: ref_15
  article-title: FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling
  publication-title: Neural Comput.
  doi: 10.1162/neco.1991.3.3.375
– ident: ref_27
– volume: 53
  start-page: 1150
  year: 2005
  ident: ref_11
  article-title: A comparative overview of microwave and wireless power-amplifier behavioral modeling approaches
  publication-title: IEEE Trans. Microw. Theory Tech.
  doi: 10.1109/TMTT.2005.845723
– volume: 5
  start-page: 366
  year: 2023
  ident: ref_12
  article-title: A new frontier for Hopfield networks
  publication-title: Nat. Rev. Phys.
  doi: 10.1038/s42254-023-00595-y
– volume: 44
  start-page: 7436
  year: 2022
  ident: ref_1
  article-title: Dynamic Neural Networks: A Survey
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2021.3117837
– volume: 52
  start-page: 417
  year: 2005
  ident: ref_4
  article-title: Global asymptotic and robust stability of recurrent neural networks with time delays
  publication-title: IEEE Trans. Circuits Syst. Regul. Pap.
  doi: 10.1109/TCSI.2004.841574
– ident: ref_19
– ident: ref_22
– ident: ref_20
– ident: ref_25
  doi: 10.1109/IWCFTA.2010.60
SSID ssj0065961
Score 2.3314855
Snippet In this paper, a new algorithm for the training of Locally Recurrent Neural Networks (LRNNs) is presented, which aims to reduce computational complexity and at...
SourceID doaj
unpaywall
proquest
gale
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
StartPage 104
SubjectTerms Algorithms
closed-form error gradient
Control stability
dynamic systems
Fibonacci numbers
gradient-based training
locally recurrent neural networks
Neural networks
Neurons
Recurrent neural networks
Stability
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1La9wwEB5KLmkPefRB3G6DSAs9mdgrS7aPu6XbENIcSgK5ibE8SgJbb9g4hPz7ztjeJUspvfRigyWENKPRzGdG3wB8JkOZ50MvJszHcVZ6H2MaGPN4m4sDDeTlNvKPc3tymZ1ematnpb4kJ6ynB-4Fd0wpodU5BR-I91dV6sx6jlHIj7FKq-70TYpyBab6M9ia0qY9j5BmUH-MwnMmyGPD-3Qk_X8exa9g-6G5w6dHnM-f-ZrZHuwMQaKa9JPbhxfUvIbdVQEGNdjjG2gm6mIo8aAm8-sFA_2bX4rDUHUmLmr-pH7K73QhYFLCwsFjnvdp3_dqyu6rVotGcQSoJBPv1t-26vuySwFr1SJ0DWe8CjVj3yf6ewuXs28XX0_ioYBC7HVh2pgM5mjYbAM7oTpJQ8FirA3xM0MsjU6oIG0KXZmEZVqaMCZG2hZrnWGd5_odbDWLhg5AJTr3PFbKr5AFKhCNqYKutOYAhUwewdFKsO6u58lwjC9E-m4t_QimIvJ1B6G27j6wwt2gcPcvhUfwRRTmxADbJXoc7hHwPIXKyk06DGkLU0Yw2ujJhuM3m1cqd4Ph3jsOpzgIzWxhI_i03gZ_X9L7_7GkD_ByLGWFu2TwEWy1ywf6yLFOWx122_o3wVX9mw
  priority: 102
  providerName: Directory of Open Access Journals
– databaseName: ProQuest Central
  dbid: BENPR
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3db9MwED-N7gH2wDciMJAFSDxFa-LYSR4QatHKhEaFpk3am-U45zGpJF2XCe2_5y51ChWCl0SKLcu-8305598BvEOFmSOlF6PN0zgrnYtt4inmcTpnA-rR8W3kr3N9dJZ9OVfnOzAf7sJwWuWgE3tFXbeOz8gPyM6Rd5DpQn9cXsVcNYr_rg4lNGworVB_6CHG7sBuyshYI9idHs6_nQy6WatSJ2t8IUnB_oFl_DOOSLasUg_e_7eK3oO7N83S3v60i8UfNmj2EO4H51FM1tx-BDvYPIYHQ2EGEeT0CTQTcRpKP4jJ4oKW0X3_Icg9Fcdsuha34oSP2RmYSTA6B405X6eDX4spmbVatI0gz1Bwht6lu-zE51WfGtaJ1vcNx7QKMSObyHx9Cmezw9NPR3EorBA7WaguRmVzq0icPRmnepz4Ar2rFdIzs7ZUcowFSlXISo2dkqXyKVIErm0tM1vnuXwGo6Zt8DmIscwdjZXQy2ceC2uVqryspCTHBVUewZuBsGa5xs8wFHcw9c2G-hFMmeSbDgx53X9oVxcmSJDBBK2WOc3RIymaqpSZpslJdKmtkiqN4D0zzLBgdivrbLhfQPNkiCsz6WNLXagygv2tniRQbrt5YLkJAn1tfm-_CN5utsG_l_Ti_4O8hHspFxLu07_3YdStbvAVeTdd9Tps2V-nifqE
  priority: 102
  providerName: ProQuest
Title A Training Algorithm for Locally Recurrent Neural Networks Based on the Explicit Gradient of the Loss Function
URI https://www.proquest.com/docview/3170854686
https://doi.org/10.3390/a18020104
https://doaj.org/article/e1ea637efcfe425b9346c533ec2ab1b2
UnpaywallVersion publishedVersion
Volume 18
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAFT
  databaseName: Open Access Digital Library
  customDbUrl:
  eissn: 1999-4893
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0065961
  issn: 1999-4893
  databaseCode: KQ8
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html
  providerName: Colorado Alliance of Research Libraries
– providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1999-4893
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0065961
  issn: 1999-4893
  databaseCode: DOA
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVEBS
  databaseName: EBSCOhost Academic Search Ultimate
  customDbUrl: https://search.ebscohost.com/login.aspx?authtype=ip,shib&custid=s3936755&profile=ehost&defaultdb=asn
  eissn: 1999-4893
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0065961
  issn: 1999-4893
  databaseCode: ABDBF
  dateStart: 20091201
  isFulltext: true
  titleUrlDefault: https://search.ebscohost.com/direct.asp?db=asn
  providerName: EBSCOhost
– providerCode: PRVEBS
  databaseName: EBSCOhost Mathematics Source - HOST
  customDbUrl:
  eissn: 1999-4893
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0065961
  issn: 1999-4893
  databaseCode: AMVHM
  dateStart: 20091201
  isFulltext: true
  titleUrlDefault: https://www.ebsco.com/products/research-databases/mathematics-source
  providerName: EBSCOhost
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1999-4893
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0065961
  issn: 1999-4893
  databaseCode: M~E
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl: http://www.proquest.com/pqcentral?accountid=15518
  eissn: 1999-4893
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0065961
  issn: 1999-4893
  databaseCode: BENPR
  dateStart: 20080301
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Technology Collection
  customDbUrl:
  eissn: 1999-4893
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0065961
  issn: 1999-4893
  databaseCode: 8FG
  dateStart: 20080301
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/technologycollection1
  providerName: ProQuest
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3db9MwED9t7QPwwPgUgVGZD4mnbE0c5-MxResmNKppWqXxZDnOGSpKOnWp0PjruUvSsoJAvCRSbFnO2ef7nX33M8BbVBhZWvR8NEnoR5m1vgkc-Tw2TtiAOrScjfxxEp9Mow-X6nIHXq1zYW6d30tyxw8NM5Sxz7AL_VgR3O5Bfzo5yz81p8VZ5jN5SssYtF1_y840dPx_Lrr34M6qujI33818fsuqjPd-5ea0wSRfD1Z1cWB__EbV-M8OP4D7HaYUeTsJHsIOVo9gb31fg-jU9zFUubjoboQQ-fzzYjmrv3wThFrFKVu0-Y0459135msSTNpBbU7aKPFrMSJrV4pFJQgwCg7cm9lZLY6XTcRYLRauKTglUYgxmUoe7icwHR9dvD_xu_sWfCtTVfuoTGIUabkjm1UOA5eis6VCekbGZEoOMUWpUlmooVUyUy5EcsxjU8rIlEkin0KvWlT4DMRQJpbaCujlIoepMUoVThZSEp5BlXjwej06-qql1dDkjrAE9UaCHox43DYVmAm7-UDy1p1iaQzQxDKhPjqk9afIZBRT5yTa0BRBEXrwjkdds77WS2NNl3ZA_WTmK503LmecqsyD_a2apGd2u3g9b3Sn59ea0Bdh1ihOYw_ebObS33_p-X_VegF3Q75muAkO34devVzhS8I-dTGA3XR8PID-6Ghydj5odhAGnUb8BEM8ApE
linkProvider Unpaywall
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwED-N7WHwwDeiY4DFh3iKlsSxkzxMqIWVjnUVmjppb5nj2GNSl5Q209R_jr-Nu9QpVAje9pJIsWXZ5_P97pz7AHhnhIk0Cj3PqDj0olRrTwUWbR4tYwJQazRFIx-P5OA0-nomzjbgZxsLQ26VrUxsBHVRaboj30OcQ-0gkon8OP3hUdUo-rvaltBQrrRCsd-kGHOBHUdmcYMm3Hz_8DPu9_sw7B-MPw08V2XA0zwRtWeEipVA3rYoqQs_sImxuhAGn5FSqeC-SQwXCc-FrwVPhQ0NmqNSFTxSRRxzHPcObEU8StH42-odjL6dtFggRSqDZT4jzlN_T1G-NbKA1lCwKRbwNyTcg-3rcqoWN2oy-QPz-g_hvlNWWXfJXY9gw5SP4UFbCII5ufAEyi4bu1ITrDu5QLLV368YqsNsSFA5WbATutanRFCMsoHgmKOl-_mc9RBGC1aVDDVRRh6Bl_qyZl9mjStazSrbNAxxFayPGEx89BROb4XEz2CzrErzHJjPY41jBfiykTWJUkLklueco6JkRNyBNy1hs-kyX0eGdg5RP1tRvwM9IvmqA6XYbj5Us4vMndjMBEZJHuMcrUHBlqc8kjg5bnSo8iAPO_CBNiwjQVDPlFYungHnSSm1sm5jy8pEpB3YXeuJB1ivN7dbnjkBMs9-s3sH3q7Y4N9L2vn_IK9hezA-HmbDw9HRC7gbUhHjxvV8Fzbr2bV5iZpVnb9y7Mvg_LZPzC_ZzjjX
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Zb9QwEB6VInE8cKMGClgc4inaJI5zPCC0pWxbuqwQaqW-BccZt5WWZNlNVe1f49cxk2NhheCtL4kUW5Y9Hs8348wB8BoVhoaEnos6DtwwNcbVviWbx0QxA6hFw9HInyfR_nH46USdbMDPPhaG3Sp7mdgI6qIyfEc-IJwj7SCMkmhgO7eIL7uj97MfLleQ4j-tfTmNlkUOcXlJ5tvi3cEu7fWbIBh9PPqw73YVBlwjE1W7qHSsFfG1JSldeL5N0JpCIT1DrVMlPUxQqkTmyjNKpsoGSKZopAsZ6iKOJY17Da7HnMWdo9RHez0KRCqN_DaTkZSpN9CcaY1tnzX8a8oE_A0Gt-HmRTnTy0s9nf6BdqN7cKdTU8Ww5av7sIHlA7jbl4AQnUR4COVQHHVFJsRwekpEqs--C1KExZhBcroUX_lCn1NACc4DQmNOWsfzhdghAC1EVQrSQQX7Ap6b81rszRsntFpUtmkY0yrEiNCXOegRHF8JgR_DZlmVuAXCk7GhsXx62dBiorVSuZW5lKQioYodeNkTNpu1mToysnCY-tmK-g7sMMlXHTi5dvOhmp9m3VnN0EcdyZjmaJFEWp7KMKLJSTSBzv08cOAtb1jGIqCea6O7SAaaJyfTyoaNFUsskTqwvdaTjq5Zb-63POtExyL7zegOvFqxwb-X9OT_g7yAG3ROsvHB5PAp3Aq4enHjc74Nm_X8Ap-RSlXnzxveFfDtqg_LL1XwNnE
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3db9MwED-N7gF4YHyKwEDmQ-IpWxPHTvKYIcqERoXQKo0ny3HOrFpJpy4V2v763SVpWUEgXhIptqLLffju4rufAd6iwsTRoheiTeMwyZ0LbeQp53E6ZQfq0XE38uexPpwkn07UyRa8WvXC3Ni_l5SO71tGKOOc4RZsa0Xh9gC2J-Mvxbd2tzjPQwZP6RCDNudv-JkWjv_PRfcu3F7W5_byp53NbniV0c6v3pyumORsb9mUe-7qN6jGfxJ8H-71MaUoOiV4AFtYP4Sd1XkNojffR1AX4rg_EUIUs-_zxbQ5_SEoahVH7NFml-Ir_31nvCbBoB30znFXJX4hDsjbVWJeCwoYBRfuTd20ER8XbcVYI-a-HTgiVogRuUoW92OYjD4cvz8M-_MWQicz1YSobGoVWbknn1UNI5-hd5VCuibW5koOMUOpMlmqoVMyVz5GSsy1rWRiqzSVT2BQz2t8CmIoU0fviujmE4-ZtUqVXpZSUjyDKg3g9Uo65ryD1TCUjjAHzZqDARyw3NYTGAm7fUD8Nr1hGYzQapkSjR5p_SlzmWgiTqKLbRmVcQDvWOqG7bVZWGf7tgOik5GvTNGmnDpTeQC7GzPJztzm8EpvTG_nF4aiL4pZE53pAN6sdenvn_Tsv2Y9hzsxHzPcFofvwqBZLPEFxT5N-bLX_ms7Bv8N
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=A+Training+Algorithm+for+Locally+Recurrent+Neural+Networks+Based+on+the+Explicit+Gradient+of+the+Loss+Function&rft.jtitle=Algorithms&rft.au=Sara+Carcangiu&rft.au=Augusto+Montisci&rft.date=2025-02-01&rft.pub=MDPI+AG&rft.eissn=1999-4893&rft.volume=18&rft.issue=2&rft.spage=104&rft_id=info:doi/10.3390%2Fa18020104&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_e1ea637efcfe425b9346c533ec2ab1b2
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1999-4893&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1999-4893&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1999-4893&client=summon