The influence of parameter initialization on the training time and accuracy of a nonlinear regression model

In order to construct a nonlinear regression model we have to accurately (in some sense) initialize parameters of the model. In this work we performed comparison of several widely used methods and several newly developed approached for initialization of parameters of a regression model, represented...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of communications technology & electronics Jg. 61; H. 6; S. 646 - 660
Hauptverfasser: Burnaev, E. V., Erofeev, P. D.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Moscow Pleiades Publishing 01.06.2016
Springer
Springer Nature B.V
Schlagworte:
ISSN:1064-2269, 1555-6557
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In order to construct a nonlinear regression model we have to accurately (in some sense) initialize parameters of the model. In this work we performed comparison of several widely used methods and several newly developed approached for initialization of parameters of a regression model, represented as a decomposition in a linear dictionary of some parametric functions (sigmoids). We proposed a general deterministic approach for initialization, providing repeatability of results, reduction of a learning time and in some cases increase of a regression model accuracy; we developed two new algorithms (based on a piecewise-linear approximation and based on local properties of approximable dependency) in the framework of the proposed approach; we developed randomized initialization algorithm (spherical initialization) for effective approximation of high-dimensional dependencies; we improved the classical initialization method SCAWI (by locating centers of sigmoids in sample points), providing a regression model accuracy improvement on specific classes of dependencies (smooth functions and discontinuous functions with a number of local peculiarities in an input domain) when using RProp algorithm for learning; we performed comparison of classical and newly proposed initialization methods and highlighted the most efficient ones.
AbstractList In order to construct a nonlinear regression model we have to accurately (in some sense) initialize parameters of the model. In this work we performed comparison of several widely used methods and several newly developed approached for initialization of parameters of a regression model, represented as a decomposition in a linear dictionary of some parametric functions (sigmoids). We proposed a general deterministic approach for initialization, providing repeatability of results, reduction of a learning time and in some cases increase of a regression model accuracy; we developed two new algorithms (based on a piecewise-linear approximation and based on local properties of approximable dependency) in the framework of the proposed approach; we developed randomized initialization algorithm (spherical initialization) for effective approximation of high-dimensional dependencies; we improved the classical initialization method SCAWI (by locating centers of sigmoids in sample points), providing a regression model accuracy improvement on specific classes of dependencies (smooth functions and discontinuous functions with a number of local peculiarities in an input domain) when using RProp algorithm for learning; we performed comparison of classical and newly proposed initialization methods and highlighted the most efficient ones.
In order to construct a nonlinear regression model we have to accurately (in some sense) initialize parameters of the model. In this work we performed comparison of several widely used methods and several newly developed approached for initialization of parameters of a regression model, represented as a decomposition in a linear dictionary of some parametric functions (sigmoids). We proposed a general deterministic approach for initialization, providing repeatability of results, reduction of a learning time and in some cases increase of a regression model accuracy; we developed two new algorithms (based on a piecewise-linear approximation and based on local properties of approximable dependency) in the framework of the proposed approach; we developed randomized initialization algorithm (spherical initialization) for effective approximation of high-dimensional dependencies; we improved the classical initialization method SCAWI (by locating centers of sigmoids in sample points), providing a regression model accuracy improvement on specific classes of dependencies (smooth functions and discontinuous functions with a number of local peculiarities in an input domain) when using RProp algorithm for learning; we performed comparison of classical and newly proposed initialization methods and highlighted the most efficient ones. Keywords: nonlinear regression, approximation, neural networks, parameter initialization, SCAWI algorithm, RProp algorithm, error back propagation algorithm DOI: 10.1134/S106422691606005X
Audience Academic
Author Burnaev, E. V.
Erofeev, P. D.
Author_xml – sequence: 1
  givenname: E. V.
  surname: Burnaev
  fullname: Burnaev, E. V.
  email: burnaev@iitp.ru
  organization: Kharkevich Institute for Information Transmission Problems, Russian Academy of Sciences
– sequence: 2
  givenname: P. D.
  surname: Erofeev
  fullname: Erofeev, P. D.
  organization: Kharkevich Institute for Information Transmission Problems, Russian Academy of Sciences
BookMark eNp9kl9r3iAUh8PoYG23D7C7wG42WFpN1Ly5LKXrCoVB_8DugtFjamf0nRpY9-l7suyib8eKguJ5HpHf8aDY88FDUbyn5IjShh1fUyJYXYuOCiII4d9fFfuUc14Jzts93GO5WupvioOU7glpOkGa_eLHzR2U1hs3g1dQBlNuZZQTZIh4bLOVzv6W2QZf4swI5yix4Mcy2wlK6XUplZqjVA-LLUt8mLMeZCwjjBFSWtwpaHBvi9dGugTv_q6Hxe2Xs5vTr9Xlt_OL05PLSjHe5YrTlqvGADeca-gUHYiWhGk20M2gDdO8hbYbWimEUYPa1ApJOjBtqAKiuuaw-Ljeu43h5wwp95NNCpyTHsKcerqpOWcd5QTRD8_Q-zBHj69DilAumGAbpI5WapQOekwrYAgKh4bJKmyEsXh-wjrBBVotCp92BGQy_MqjnFPqL66vdtnPT9hhThgehuaTHe9yWpUdvF1xFUNKEUyvbP7ToKUxrqekXz5E_8-HQJM-M7fRTjI-vOjUq5OQ9SPEJ_n8V3oEzUfI0g
CitedBy_id crossref_primary_10_1007_s10462_021_10033_z
crossref_primary_10_1134_S1064226919120039
crossref_primary_10_1007_s10472_017_9545_y
crossref_primary_10_1016_j_petrol_2020_107504
crossref_primary_10_1016_j_cageo_2019_02_002
crossref_primary_10_1016_j_petrol_2019_05_055
crossref_primary_10_1016_j_advengsoft_2016_09_001
crossref_primary_10_3390_sym13050758
Cites_doi 10.1016/j.neucom.2003.10.014
10.1002/wics.53
10.1134/S0005117913100044
10.1007/3-7643-7356-3_19
10.1109/IJCNN.1990.137819
10.1137/060657704
10.1016/0893-6080(95)00071-2
10.1007/s005210050006
10.1109/72.728357
10.1093/oso/9780198523963.001.0001
ContentType Journal Article
Copyright Pleiades Publishing, Inc. 2016
COPYRIGHT 2016 Springer
Copyright_xml – notice: Pleiades Publishing, Inc. 2016
– notice: COPYRIGHT 2016 Springer
DBID AAYXX
CITATION
N95
ISR
3V.
7SP
7WY
7WZ
7XB
87Z
88I
88K
8AO
8FD
8FE
8FG
8FK
8FL
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BEZIV
BGLVJ
CCPQU
DWQXO
FRNLG
F~G
GNUQQ
HCIFZ
JQ2
K60
K6~
K7-
L.-
L7M
M0C
M2P
M2T
P5Z
P62
PHGZM
PHGZT
PKEHL
PQBIZ
PQBZA
PQEST
PQGLB
PQQKQ
PQUKI
PYYUZ
Q9U
DOI 10.1134/S106422691606005X
DatabaseName CrossRef
Gale Business: Insights
Gale In Context: Science
ProQuest Central (Corporate)
Electronics & Communications Abstracts
ABI/INFORM Collection
ABI/INFORM Global (PDF only)
ProQuest Central (purchase pre-March 2016)
ABI/INFORM Collection
Science Database (Alumni Edition)
Telecommunications (Alumni Edition)
ProQuest Pharma Collection
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central (Alumni) (purchase pre-March 2016)
ABI/INFORM Collection (Alumni)
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials - QC
ProQuest Central
Business Premium Collection
Technology Collection
ProQuest One
ProQuest Central Korea
Business Premium Collection (Alumni)
ABI/INFORM Global (Corporate)
ProQuest Central Student
SciTech Premium Collection
ProQuest Computer Science Collection
ProQuest Business Collection (Alumni Edition)
ProQuest Business Collection
Computer Science Database
ABI/INFORM Professional Advanced
Advanced Technologies Database with Aerospace
ABI/INFORM Global
Science Database
Telecommunications Database
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic (New)
ProQuest One Academic Middle East (New)
ProQuest One Business
ProQuest One Business (Alumni)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ABI/INFORM Collection China
ProQuest Central Basic
DatabaseTitle CrossRef
ABI/INFORM Global (Corporate)
ProQuest Business Collection (Alumni Edition)
ProQuest One Business
Computer Science Database
ProQuest Central Student
Technology Collection
Technology Research Database
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Pharma Collection
ABI/INFORM Complete
ProQuest Telecommunications
ProQuest Central
ABI/INFORM Professional Advanced
ProQuest One Applied & Life Sciences
ProQuest Central Korea
ProQuest Central (New)
Advanced Technologies Database with Aerospace
ABI/INFORM Complete (Alumni Edition)
Advanced Technologies & Aerospace Collection
Business Premium Collection
ABI/INFORM Global
ProQuest Science Journals (Alumni Edition)
ABI/INFORM Global (Alumni Edition)
ProQuest Central Basic
ProQuest Science Journals
ProQuest One Academic Eastern Edition
Electronics & Communications Abstracts
ABI/INFORM China
ProQuest Technology Collection
ProQuest Telecommunications (Alumni Edition)
ProQuest SciTech Collection
ProQuest Business Collection
Advanced Technologies & Aerospace Database
ProQuest One Academic UKI Edition
ProQuest One Business (Alumni)
ProQuest One Academic
ProQuest Central (Alumni)
ProQuest One Academic (New)
Business Premium Collection (Alumni)
DatabaseTitleList

ABI/INFORM Global (Corporate)


Technology Research Database
Database_xml – sequence: 1
  dbid: BENPR
  name: ProQuest Central
  url: https://www.proquest.com/central
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1555-6557
EndPage 660
ExternalDocumentID 4107776171
A496568017
10_1134_S106422691606005X
Genre Feature
GroupedDBID -5B
-5G
-BR
-EM
-Y2
-~C
.4S
.DC
.VR
06D
0R~
0VY
1N0
29K
29~
2J2
2JN
2JY
2KG
2KM
2LR
2VQ
2~H
30V
3V.
4.4
408
40D
40E
5GY
5VS
6NX
7WY
88I
8AO
8FE
8FG
8FL
8TC
8UJ
95-
95.
95~
96X
AAAVM
AABHQ
AACDK
AAHNG
AAIAL
AAJBT
AAJKR
AANZL
AARHV
AARTL
AASML
AATNV
AATVU
AAUYE
AAWCG
AAYIU
AAYQN
AAYTO
AAYZH
ABAKF
ABBBX
ABDPE
ABDZT
ABECU
ABFTV
ABHLI
ABHQN
ABJNI
ABJOX
ABKCH
ABKTR
ABMNI
ABMQK
ABNWP
ABQBU
ABQSL
ABSXP
ABTEG
ABTHY
ABTKH
ABTMW
ABULA
ABUWG
ABWNU
ABXPI
ACAOD
ACBEA
ACBXY
ACDTI
ACGFO
ACGFS
ACGOD
ACHSB
ACHXU
ACKNC
ACMDZ
ACMLO
ACOKC
ACOMO
ACPIV
ACREN
ACSNA
ACZOJ
ADHHG
ADHIR
ADINQ
ADKNI
ADKPE
ADMLS
ADRFC
ADTPH
ADURQ
ADYFF
ADYOE
ADZKW
AEBTG
AEFQL
AEGAL
AEGNC
AEJHL
AEJRE
AEKMD
AEMSY
AENEX
AEOHA
AEPYU
AETLH
AEVLU
AEXYK
AFBBN
AFFNX
AFGCZ
AFKRA
AFLOW
AFQWF
AFWTZ
AFYQB
AFZKB
AGAYW
AGDGC
AGJBK
AGMZJ
AGQMX
AGRTI
AGWIL
AGWZB
AGYKE
AHAVH
AHBYD
AHKAY
AHSBF
AHYZX
AIAKS
AIGIU
AIIXL
AILAN
AITGF
AJBLW
AJRNO
ALMA_UNASSIGNED_HOLDINGS
ALWAN
AMKLP
AMTXH
AMXSW
AMYLF
AMYQR
AOCGG
ARAPS
ARCSS
ARMRJ
ASPBG
AVWKF
AXYYD
AZFZN
AZQEC
B-.
BA0
BAAKF
BDATZ
BENPR
BEZIV
BGLVJ
BGNMA
BPHCQ
BSONS
CAG
CCPQU
COF
CS3
CSCUP
D-I
DDRTE
DNIVK
DPUIP
DU5
DWQXO
EBLON
EBS
EIOEI
EJD
ESBYG
FEDTE
FERAY
FFXSO
FIGPU
FINBP
FNLPD
FRNLG
FRRFC
FSGXE
FWDCC
GGCAI
GGRSB
GJIRD
GNUQQ
GNWQR
GQ6
GQ7
GROUPED_ABI_INFORM_COMPLETE
H13
HCIFZ
HF~
HG6
HLICF
HMJXF
HRMNR
HVGLF
HZ~
IAO
IJ-
IKXTQ
ISR
IWAJR
IXD
I~X
I~Z
J-C
JBSCW
JZLTJ
K60
K6~
KOV
LLZTM
M0C
M2P
M4Y
MA-
MK~
ML~
N2Q
N95
NB0
NPVJJ
NQJWS
NU0
O9-
O93
O9J
P62
P9P
PF0
PQBIZ
PQBZA
PQQKQ
PROAC
PT4
Q2X
QOS
R89
R9I
RNS
ROL
RSV
S16
S1Z
S27
S3B
SAP
SDH
SEG
SHX
SISQX
SJYHP
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
STPWE
SZN
T13
TSG
TUC
TUS
UG4
UOJIU
UTJUX
UZXMN
VC2
VFIZW
W23
W48
WK8
XI7
XU3
YLTOR
Z7R
Z7X
Z83
Z88
ZMTXR
~A9
AAPKM
AAYXX
ABDBE
ABFSG
ABRTQ
ACSTC
ADHKG
AEZWR
AFDZB
AFFHD
AFHIU
AFOHR
AGQPQ
AHPBZ
AHWEU
AIXLP
ATHPR
CITATION
K7-
PHGZM
PHGZT
PQGLB
7SP
7XB
88K
8FD
8FK
JQ2
L.-
L7M
M2T
PKEHL
PQEST
PQUKI
PUEGO
Q9U
ID FETCH-LOGICAL-c459t-5175c3fe5f55de9c1b0da04d4b18bdf4d57e79b7a66fcbc82c5f51b4df1ce0c93
IEDL.DBID RSV
ISICitedReferencesCount 17
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000379343100011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1064-2269
IngestDate Thu Oct 02 10:09:17 EDT 2025
Wed Sep 17 23:58:01 EDT 2025
Tue Nov 04 17:29:03 EST 2025
Thu Nov 13 15:51:19 EST 2025
Sat Nov 29 09:15:04 EST 2025
Sat Nov 29 03:05:31 EST 2025
Tue Nov 18 21:30:22 EST 2025
Fri Feb 21 02:38:32 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 6
Keywords parameter initialization
nonlinear regression
approximation
neural networks
RProp algorithm
SCAWI algorithm
error back propagation algorithm
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c459t-5175c3fe5f55de9c1b0da04d4b18bdf4d57e79b7a66fcbc82c5f51b4df1ce0c93
Notes SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
PQID 1801564648
PQPubID 54180
PageCount 15
ParticipantIDs proquest_miscellaneous_1825549150
proquest_journals_1801564648
gale_infotracacademiconefile_A496568017
gale_incontextgauss_ISR_A496568017
gale_businessinsightsgauss_A496568017
crossref_citationtrail_10_1134_S106422691606005X
crossref_primary_10_1134_S106422691606005X
springer_journals_10_1134_S106422691606005X
PublicationCentury 2000
PublicationDate 20160600
2016-6-00
20160601
PublicationDateYYYYMMDD 2016-06-01
PublicationDate_xml – month: 6
  year: 2016
  text: 20160600
PublicationDecade 2010
PublicationPlace Moscow
PublicationPlace_xml – name: Moscow
– name: Silver Spring
PublicationTitle Journal of communications technology & electronics
PublicationTitleAbbrev J. Commun. Technol. Electron
PublicationYear 2016
Publisher Pleiades Publishing
Springer
Springer Nature B.V
Publisher_xml – name: Pleiades Publishing
– name: Springer
– name: Springer Nature B.V
References Fernández-Redondo, Hernandez-Espinosa (CR16) 2001
Kolen, Pollack (CR3) 1990
Houkes (CR10) 2000
Joseph, Ying (CR21) 2008; 18
Maiorov, Oskolkov, Temlyakov (CR19) 2002
Sutton, Szepesvári, Geramifard, Bowling, McAllester, Myllymaki (CR8) 2008
Nguyen, Widrow (CR17) 1990
Pavelka, Procházka (CR18) 2004
Oja (CR6) 1996; 9
Bowman, Azzalini (CR23) 1997
Belyaev, Burnaev (CR11) 2013; 7
Thimm, Fiesler (CR7) 1997
Burnaev, Prikhodko (CR13) 2013; 74
Zhang, Chen, Ansari, Shi (CR9) 2004; 57
Hush, Horne (CR22) 1998; 9
Fontenla-Romero, Erdogmus, Principe, Alonso-Betanzos, Castillo (CR14) 2003
Bruckstein, Donoho, Elad (CR20) 2009; 51
Hyder, Shahid, Kashem, Islam (CR5) 2009
Banks (CR2) 2010; 2
Bernstein, Burnaev, Kuleshov (CR1) 2010
Drago, Ridella (CR4) 1999; 8
Igel, Toussaint, Weishui, Mache, Szabados, De Bruin (CR15) 2005
Grihon, Burnaev, Belyaev, Prikhodko (CR12) 2013
A. Bruckstein (292_CR20) 2009; 51
A. Bernstein (292_CR1) 2010
J. Kolen (292_CR3) 1990
R. Sutton (292_CR8) 2008
Z. Houkes (292_CR10) 2000
M. Fernández-Redondo (292_CR16) 2001
D. Banks (292_CR2) 2010; 2
E. Oja (292_CR6) 1996; 9
E. Burnaev (292_CR13) 2013; 74
A. Pavelka (292_CR18) 2004
V. Maiorov (292_CR19) 2002
O. Fontenla-Romero (292_CR14) 2003
G. Drago (292_CR4) 1999; 8
X. M. Zhang (292_CR9) 2004; 57
M. Belyaev (292_CR11) 2013; 7
G. Thimm (292_CR7) 1997
D. Nguyen (292_CR17) 1990
D. Hush (292_CR22) 1998; 9
M. Hyder (292_CR5) 2009
S. Grihon (292_CR12) 2013
A. Bowman (292_CR23) 1997
C. Igel (292_CR15) 2005
V. Joseph (292_CR21) 2008; 18
References_xml – volume: 18
  start-page: 171
  year: 2008
  end-page: 186
  ident: CR21
  article-title: Orthogonal-Maximin Latin Hypercube Designs
  publication-title: Stat. Sinica
– year: 1997
  ident: CR7
  publication-title: Optimal Setting of Weights, Learning Rate and Gain
– start-page: 119
  year: 2001
  end-page: 124
  ident: CR16
  article-title: Weight initialization methods for multilayer feedforward
  publication-title: Proc. 9th Eur. Symp. on Artificial Neural Networks (ESANN-2001), Bruges, Belgium, Apr. 25–27, 2001
– volume: 57
  start-page: 389
  year: 2004
  end-page: 409
  ident: CR9
  article-title: Mini-max initialization for function approximation
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2003.10.014
– start-page: 255
  year: 2003
  end-page: 260
  ident: CR14
  article-title: Accelerating the convergence speed of neural networks learning methods using least squares
  publication-title: Proc. 11th Eur. Symp. on Artificial Neural Networks (ESANN 2003), Bruges, Belgium, April 23–25, 2003
– start-page: 291
  year: 2000
  end-page: 296
  ident: CR10
  article-title: Incorporating a priori knowledge into initialized weights for neural classifier
  publication-title: Proc. IEEEINNS-ENNS Int. Joint Conf. on Neural Networks (IJCNN), Como, Italy, July 24–27, 2000; Neural Computing: New Challenges and Perspectives for the New Millennium, IEEE, 2000
– volume: 2
  start-page: 9
  year: 2010
  end-page: 25
  ident: CR2
  article-title: Statistical data mining
  publication-title: Wiley Interdisciplinary Reviews: Comput. Stat.
  doi: 10.1002/wics.53
– start-page: 359
  year: 2013
  end-page: 391
  ident: CR12
  publication-title: Surrogate Modeling of Stability Constraints for Optimization of Composite Structures in Springer Series in Computational Science & Engineering
– year: 2009
  ident: CR5
  article-title: Initial weight determination of a MLP for faster convergence
  publication-title: J. Electron. Comput. Sci.
– start-page: 528
  year: 2008
  end-page: 536
  ident: CR8
  article-title: Dyna-style planning with linear function approximation and prioritized sweeping
  publication-title: Proc. 24th Conf. in Uncertainty in Artificial Intelligence (UAI’ 2008), Helsinki, Finland, July 9–12, 2008
– start-page: 284
  year: 2002
  end-page: 309
  ident: CR19
  publication-title: Gridge approximation and Radon compass
– start-page: 453
  year: 2004
  end-page: 459
  ident: CR18
  article-title: Algorithms for initialization of neural network weights
  publication-title: Sborník Príspevku 12 Rocníku Konf. MATLAB 2004
– volume: 74
  start-page: 1630
  year: 2013
  end-page: 1644
  ident: CR13
  article-title: On a method for constructing ensembles of regression models
  publication-title: Autom. Remote Control
  doi: 10.1134/S0005117913100044
– year: 1997
  ident: CR23
  publication-title: Applied Smoothing Techniques for Data Analysis: The Kernel Approach with S-Plus Illustrations (Oxford Statistical Science Series)
– start-page: 259
  year: 2005
  end-page: 272
  ident: CR15
  article-title: Rprop using the natural gradient
  publication-title: Trends and Applications in Constructive Approximation
  doi: 10.1007/3-7643-7356-3_19
– start-page: 21
  year: 1990
  end-page: 26
  ident: CR17
  article-title: Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights
  publication-title: Proc. Int. Joint Conf. on Neural Networks (IJCNN), IEEE, June, 1990
  doi: 10.1109/IJCNN.1990.137819
– volume: 51
  start-page: 34
  year: 2009
  end-page: 81
  ident: CR20
  article-title: From sparse solutions of systems of equations to sparse modeling of signals and images
  publication-title: SIAM Rev.
  doi: 10.1137/060657704
– volume: 9
  start-page: 435
  year: 1996
  end-page: 444
  ident: CR6
  article-title: Robust fitting by nonlinear neural units
  publication-title: Neural Networks
  doi: 10.1016/0893-6080(95)00071-2
– volume: 8
  start-page: 40
  issue: 1
  year: 1999
  end-page: 52
  ident: CR4
  article-title: Possibility and necessity pattern classification using an interval arithmetic perceptron
  publication-title: Neural Comput. Appl.
  doi: 10.1007/s005210050006
– year: 1990
  ident: CR3
  article-title: Back propagation is sensitive to initial conditions
  publication-title: Proc. 1990 Conf. on Advances in Neural Information Processing Systems 3, (NIPS-3), San Francisco, CA, USA, 1990
– start-page: 64
  year: 2010
  end-page: 71
  ident: CR1
  article-title: Adaptive models of complex systems based on data handling
  publication-title: Proc. 3rd Int. Conf. on Inductive Modelling ICIM-2010, Kyiv, Ukraine, May 16–22, 2010
– volume: 7
  start-page: 114
  year: 2013
  end-page: 125
  ident: CR11
  article-title: Approximation of a multidimensional dependency based on a linear expansion in a dictionary of parametric functions
  publication-title: Inform. Appl.
– volume: 9
  start-page: 1129
  year: 1998
  end-page: 1141
  ident: CR22
  article-title: Efficient algorithms for function approximation with piecewise linear sigmoidal networks
  publication-title: IEEE Trans. on Neural Networks
  doi: 10.1109/72.728357
– start-page: 259
  volume-title: Trends and Applications in Constructive Approximation
  year: 2005
  ident: 292_CR15
  doi: 10.1007/3-7643-7356-3_19
– volume: 9
  start-page: 1129
  year: 1998
  ident: 292_CR22
  publication-title: IEEE Trans. on Neural Networks
  doi: 10.1109/72.728357
– volume: 8
  start-page: 40
  issue: 1
  year: 1999
  ident: 292_CR4
  publication-title: Neural Comput. Appl.
  doi: 10.1007/s005210050006
– start-page: 359
  volume-title: Surrogate Modeling of Stability Constraints for Optimization of Composite Structures in Springer Series in Computational Science & Engineering
  year: 2013
  ident: 292_CR12
– start-page: 284
  volume-title: Gridge approximation and Radon compass
  year: 2002
  ident: 292_CR19
– start-page: 453
  volume-title: Sborník Príspevku 12 Rocníku Konf. MATLAB 2004
  year: 2004
  ident: 292_CR18
– volume: 18
  start-page: 171
  year: 2008
  ident: 292_CR21
  publication-title: Stat. Sinica
– volume-title: Applied Smoothing Techniques for Data Analysis: The Kernel Approach with S-Plus Illustrations (Oxford Statistical Science Series)
  year: 1997
  ident: 292_CR23
  doi: 10.1093/oso/9780198523963.001.0001
– volume: 7
  start-page: 114
  year: 2013
  ident: 292_CR11
  publication-title: Inform. Appl.
– volume-title: Proc. 1990 Conf. on Advances in Neural Information Processing Systems 3, (NIPS-3), San Francisco, CA, USA, 1990
  year: 1990
  ident: 292_CR3
– volume: 51
  start-page: 34
  year: 2009
  ident: 292_CR20
  publication-title: SIAM Rev.
  doi: 10.1137/060657704
– start-page: 255
  volume-title: Proc. 11th Eur. Symp. on Artificial Neural Networks (ESANN 2003), Bruges, Belgium, April 23–25, 2003
  year: 2003
  ident: 292_CR14
– start-page: 21
  volume-title: Proc. Int. Joint Conf. on Neural Networks (IJCNN), IEEE, June, 1990
  year: 1990
  ident: 292_CR17
  doi: 10.1109/IJCNN.1990.137819
– volume: 9
  start-page: 435
  year: 1996
  ident: 292_CR6
  publication-title: Neural Networks
  doi: 10.1016/0893-6080(95)00071-2
– start-page: 291
  volume-title: Proc. IEEEINNS-ENNS Int. Joint Conf. on Neural Networks (IJCNN), Como, Italy, July 24–27, 2000; Neural Computing: New Challenges and Perspectives for the New Millennium, IEEE, 2000
  year: 2000
  ident: 292_CR10
– start-page: 119
  volume-title: Proc. 9th Eur. Symp. on Artificial Neural Networks (ESANN-2001), Bruges, Belgium, Apr. 25–27, 2001
  year: 2001
  ident: 292_CR16
– volume-title: Optimal Setting of Weights, Learning Rate and Gain
  year: 1997
  ident: 292_CR7
– start-page: 64
  volume-title: Proc. 3rd Int. Conf. on Inductive Modelling ICIM-2010, Kyiv, Ukraine, May 16–22, 2010
  year: 2010
  ident: 292_CR1
– volume-title: J. Electron. Comput. Sci.
  year: 2009
  ident: 292_CR5
– volume: 57
  start-page: 389
  year: 2004
  ident: 292_CR9
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2003.10.014
– volume: 74
  start-page: 1630
  year: 2013
  ident: 292_CR13
  publication-title: Autom. Remote Control
  doi: 10.1134/S0005117913100044
– start-page: 528
  volume-title: Proc. 24th Conf. in Uncertainty in Artificial Intelligence (UAI’ 2008), Helsinki, Finland, July 9–12, 2008
  year: 2008
  ident: 292_CR8
– volume: 2
  start-page: 9
  year: 2010
  ident: 292_CR2
  publication-title: Wiley Interdisciplinary Reviews: Comput. Stat.
  doi: 10.1002/wics.53
SSID ssj0039603
Score 2.1671379
Snippet In order to construct a nonlinear regression model we have to accurately (in some sense) initialize parameters of the model. In this work we performed...
SourceID proquest
gale
crossref
springer
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 646
SubjectTerms Accuracy
Algorithms
Approximation
Artificial neural networks
Communications Engineering
Communications equipment
Communications technology
Comparative analysis
Decomposition
Dependence
Dictionaries
Engineering
Experiments
Learning
Mathematical analysis
Mathematical models
Mathematical Models and Computational Methods
Mean square errors
Networks
Neural networks
Nonlinear systems
Nonlinearity
Regression
Regression analysis
Studies
Support vector machines
SummonAdditionalLinks – databaseName: Science Database
  dbid: M2P
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB5B4QAH3hWBFhkEQgJZzcN5naqqagUHqoqCtLfIHtvVipItyS4S_56ZxCldKnpBinJwxnGsmYw_2-P5AF57gqh8KFdmaeylKtBIY8tMOq_qVNfeu9wMZBPl0VE1m9XHYcGtD2GVk08cHLVdIK-R7yQVH_pVhap2z39IZo3i3dVAoXETbhGySTik61N6PHnijND5GGBfKEkwow67mkmmdk64kMsSQvBkibO1celv73xlm3QYfQ7v_-93P4B7AXeKvdFQHsIN1z6Cu5eyET6Gb2QyYj6RloiFF5wX_DvHy1DxnFzBWTi0Kegi4CgmfgnBDPVCt1ZoxFWn8RfX1qId83DoTnTudAy4bcXAvfMEvh4efNn_IAMXg0SV10uZE8zAjDTn89y6GhMTWx0rq0xSGeuVzUtX1qbUReHRYJUiSSZGWZ-gi7HONmGDGnVPQcSaYIsmJ4uVUq6iGZpHAm2a7MKXqU0jiCdNNBgSlXN_zpphwpKp5oryInh3UeV8zNJxnfAbVm8TWD7p1vM6SH-qV33f7HEC_YKUVkbwapDjLBkth-GMAh9PPq8JvQ1CfkEfiTqcaqCucmKtNcmtyUCa4Cf65o91RPDy4jH94bxto1u3WLEMTftUTcg9gveTGV56xb_6-ez6Bp_DHQJ_xRj2tgUby27ltuE2_lzO--7F8CP9Blu7I10
  priority: 102
  providerName: ProQuest
Title The influence of parameter initialization on the training time and accuracy of a nonlinear regression model
URI https://link.springer.com/article/10.1134/S106422691606005X
https://www.proquest.com/docview/1801564648
https://www.proquest.com/docview/1825549150
Volume 61
WOSCitedRecordID wos000379343100011&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: PRVPQU
  databaseName: ABI/INFORM Collection
  customDbUrl:
  eissn: 1555-6557
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0039603
  issn: 1064-2269
  databaseCode: 7WY
  dateStart: 20060201
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/abicomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ABI/INFORM Global
  customDbUrl:
  eissn: 1555-6557
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0039603
  issn: 1064-2269
  databaseCode: M0C
  dateStart: 20060201
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/abiglobal
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 1555-6557
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0039603
  issn: 1064-2269
  databaseCode: P5Z
  dateStart: 20060201
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 1555-6557
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0039603
  issn: 1064-2269
  databaseCode: K7-
  dateStart: 20060201
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1555-6557
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0039603
  issn: 1064-2269
  databaseCode: BENPR
  dateStart: 20060201
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Science Database
  customDbUrl:
  eissn: 1555-6557
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0039603
  issn: 1064-2269
  databaseCode: M2P
  dateStart: 20060201
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/sciencejournals
  providerName: ProQuest
– providerCode: PRVAVX
  databaseName: SpringerLINK Contemporary 1997-Present
  customDbUrl:
  eissn: 1555-6557
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0039603
  issn: 1064-2269
  databaseCode: RSV
  dateStart: 20060101
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3db9MwED-xjQd44BsRGJVBICSQRT6cOHkc0yYQoqraAYWXyHbsqdqWoqRF4r_nLnGmlQESSNVJbX9J4-R893N9HwDPHFJUSsrlSRw6LjKjua5kwq0TRawK52yqu2YTcjzO5_Ni4vO42yHafdiS7Cx133dEvJ5FxJXjDPlMiF46nW_BDnq7nPo1TGefBvObICXvo-ozwQnutzJ_e4oNZ_SrSb60N9q5nMOb_3Wxt-CGZ5hsr1eJ23DF1nfg-oW6g3fhBJWDLYb2JGzpGFUAP6PIGPx4gZP-1KdnMnwhRWRDJwlGveiZqiumjFk3yvygoxWr-4obqmGNPe5Da2vWddm5Bx8PD47233LfdYEbkRYrniKhMAk-I5emlS1MpMNKhaISOsp15USVSisLLVWWOaNNHhtERlpULjI2NEVyH7bxR-0DYKFCgqLQnJpcCJvjWswZpGcKNcDJuIoDCIfbXxpfkpzGc1p2S5NElJfuYwAvzw_51tfj-Bv4OT3T0vfzRNHSPx7tsVq3bblHpfIz9NAygKcdjuph1BRw0wPezaYboBce5JZ4kUb5_AUcKpXQ2kDuDjpUeovQllFOSesiE3kAT86_xrlMGzSqtss1YXCBJwrk6AG8GvTqwin-NM6H_4R-BNeQ9WV9vNsubK-atX0MV8331aJtRrAlP38Zwc6bg_Fkiu_eS47yQ7hPMp508gjlJP066ibeTzQ6H6o
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1bT9RAFD4haKI-4JVQQB2NxETT0Mv09mAMUQkbcEMEk32r07mQjdDFdhfDn_I3ek47g6xE3ngw2ezD9HTb2Z45l8453wfwymCISk25fhwFxueprPxKZbGvDS8iURijk6ojm8iGw3w0KvYX4JfrhaGySmcTO0OtJpLekW-GOTX98pTn709_-MQaRburjkKjV4tdff4TU7b23eAjPt-NKNr-dPhhx7esAr7kSTH1E3SYMsZ7MEmidCHDKlAi4IpXYV4pw1WS6ayoMpGmRlYyjyRKhhVXJpQ6kAS-hCb_FidkMSoVjPad5Y8xG-gL-lPuY1hT2F3UMOabBzRIYyFmDKj5ozk_-Lc3uLIt23m77fv_2__0AJZsXM22-oXwEBZ0_QjuXUJbfAzfcUmwsSNlYRPDCPf8hOqBcHiMpu7YNqUy_GBgzBx_BpuOTzQTtWJCylkj5DmdLVjd44yIhjX6qC8orlnHLfQEvt7IbJdhES-qV4AFAsMygU5E5pzrHDNQIzEoFaj3JotU5EHgnnwpLRA7zee47BKymJdXlMWDNxennPYoJNcJb5A6lZbFFL9aes_THolZ25ZbRBCQopJkHrzs5AgFpKYyo15gcPBlTui1FTITvEkpbNcGTpWAw-Yk151CltYOtuUfbfTgxcVhtGC0LSVqPZmRDKa1vMDMxIO3Tu0v_cS_5rl6_QWfw52dw8975d5guLsGdzHQTfsSv3VYnDYz_RRuy7PpuG2edYuYwbebXg2_AQRohAI
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1ta9RAEB60iugH38Vo1VUUoRKal83bx6IeFuUonsp9C7uzu-VomyvJneC_dybZlJ5VQYRwH3JPkt3byeyztzPPALx0RFE5KTdMk8iFMkcdalOkoXWySlTlnM10X2yimE7L-bw68HVOuzHafdySHHIaWKWpWe2eGudrkMjdWcy8OcmJ20Q0Y2fzy3BFchw9L9dn30ZXnBI9HyLscxky3G9r_vYWGxPTr-75wj5pP_1Mbv13w2_DTc88xd5gKnfgkm3uwo1zeoT34IiMRizGsiVi6QQrg59wxAydXpAzOPZpm4IOoo5irDAhuEa9UI0RCnHdKvzBVyvRDEocqhWtPRxCbhvRV9-5D18n77-8_RD6agwhyqxahRkRDUxp7FyWGVthrCOjImmkjkttnDRZYYtKFyrPHWosEyRkrKVxMdoIq_QBbNFD7UMQkSLiosjNYimlLWmN5pBomyLLcEVikgCicShq9FLl3J_jul-ypLK-8DsGsHN2yemg0_E38Cse39rX-aSPjv8J6Q7VuuvqPZbQz2nmLgJ40eNYJ6PhQJwBsD_7vAF67UFuSY1E5fMaqKssrbWB3B7tqfaeoqvjkpPZZS7LAJ6ffU3vOG_cqMYu14yhhZ-siLsH8Ga0sXO3-FM_H_0T-hlcO3g3qT_tTz8-hutEDPMhJG4btlbt2j6Bq_h9tejap_079hMkpCQ7
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=The+influence+of+parameter+initialization+on+the+training+time+and+accuracy+of+a+nonlinear+regression+model&rft.jtitle=Journal+of+communications+technology+%26+electronics&rft.au=Burnaev%2C+E.V&rft.au=Erofeev%2C+P.D&rft.date=2016-06-01&rft.pub=Springer&rft.issn=1064-2269&rft.volume=61&rft.issue=6&rft.spage=646&rft_id=info:doi/10.1134%2FS106422691606005X&rft.externalDocID=A496568017
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1064-2269&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1064-2269&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1064-2269&client=summon