A new efficient training strategy for deep neural networks by hybridization of artificial bee colony and limited–memory BFGS optimization algorithms

Working up with deep learning techniques requires profound understanding of the mechanisms underlying the optimization of the internal parameters of complex structures. The major factor limiting this understanding is that there exist only a few optimization methods such as gradient descent and Limit...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Neurocomputing (Amsterdam) Ročník 266; s. 506 - 526
Hlavní autoři: Badem, Hasan, Basturk, Alper, Caliskan, Abdullah, Yuksel, Mehmet Emin
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 29.11.2017
Témata:
ISSN:0925-2312, 1872-8286
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Working up with deep learning techniques requires profound understanding of the mechanisms underlying the optimization of the internal parameters of complex structures. The major factor limiting this understanding is that there exist only a few optimization methods such as gradient descent and Limited–memory Broyden–Fletcher–Goldfarb–Shannon (L-BFGS) to find the best local minima of the problem space for these complex structures such as deep neural network (DNN). Therefore, in this paper, we represent a new training approach named hybrid artificial bee colony based training strategy (HABCbTS) to tune the parameters of a DNN structure, which includes one or more autoencoder layers cascaded to a softmax classification layer. In this strategy, a derivative-free optimization algorithm “ABC” is combined with a derivative-based algorithm “L-BFGS” to construct “HABC”, which is used in the HABCbTS. Detailed simulation results supported by statistical analysis show that the proposed training strategy results in better classification performance compared to the DNN classifier trained with the L-BFGS, ABC and modified ABC. The obtained classification results are also compared with the state-of-the-art classifiers, including MLP, SVM, KNN, DT and NB on 15 data sets with different dimensions and sizes.
AbstractList Working up with deep learning techniques requires profound understanding of the mechanisms underlying the optimization of the internal parameters of complex structures. The major factor limiting this understanding is that there exist only a few optimization methods such as gradient descent and Limited–memory Broyden–Fletcher–Goldfarb–Shannon (L-BFGS) to find the best local minima of the problem space for these complex structures such as deep neural network (DNN). Therefore, in this paper, we represent a new training approach named hybrid artificial bee colony based training strategy (HABCbTS) to tune the parameters of a DNN structure, which includes one or more autoencoder layers cascaded to a softmax classification layer. In this strategy, a derivative-free optimization algorithm “ABC” is combined with a derivative-based algorithm “L-BFGS” to construct “HABC”, which is used in the HABCbTS. Detailed simulation results supported by statistical analysis show that the proposed training strategy results in better classification performance compared to the DNN classifier trained with the L-BFGS, ABC and modified ABC. The obtained classification results are also compared with the state-of-the-art classifiers, including MLP, SVM, KNN, DT and NB on 15 data sets with different dimensions and sizes.
Author Badem, Hasan
Yuksel, Mehmet Emin
Caliskan, Abdullah
Basturk, Alper
Author_xml – sequence: 1
  givenname: Hasan
  surname: Badem
  fullname: Badem, Hasan
  email: hbadem@erciyes.edu.tr
  organization: Department of Computer Engineering, Erciyes University, Kayseri, Turkey
– sequence: 2
  givenname: Alper
  orcidid: 0000-0001-5810-0643
  surname: Basturk
  fullname: Basturk, Alper
  organization: Department of Computer Engineering, Erciyes University, Kayseri, Turkey
– sequence: 3
  givenname: Abdullah
  surname: Caliskan
  fullname: Caliskan, Abdullah
  organization: Department of Biomedical Engineering, Erciyes University, Kayseri, Turkey
– sequence: 4
  givenname: Mehmet Emin
  surname: Yuksel
  fullname: Yuksel, Mehmet Emin
  organization: Department of Biomedical Engineering, Erciyes University, Kayseri, Turkey
BookMark eNqFkM9O3DAQh60KpC5_3qAHv0DC2Nl4Nz1UWhBQJKQegLPlOONdbxN7ZZuicOo7VOoD8iQ4XU4cymlGo9_3k-Y7IgfOOyTkC4OSARNn29Lho_ZDyYEtSqhLEOwTmbHlghdLvhQHZAYNrwteMf6ZHMW4hRxkvJmRvyvq8ImiMVZbdImmoKyzbk1j3hKuR2p8oB3iLgcfg-rzSE8-_Iy0HelmbIPt7LNK1jvqDVUh2akq51pEqn3v3UiV62hvB5uwe_n9Z8DBh5GeX13fUb9L-f7Gq37tg02bIZ6QQ6P6iKdv85g8XF3eX3wvbn9c31ysbgtdLXgqFNQKtDDzrgIzb4WApmFCKA2atY1uDKuMQOgUcsMYa0xrljVv6jlfMA0GqmMy3_fq4GMMaOQu2EGFUTKQk1u5lXu3cnIroZbZbca-vsO0Tf9-mPT1H8Hf9jDmx35ZDDJO6jV2NqBOsvP2_wWvJTCfVQ
CitedBy_id crossref_primary_10_3390_nano15161289
crossref_primary_10_1007_s11661_018_4984_6
crossref_primary_10_1016_j_asoc_2020_106656
crossref_primary_10_1109_TII_2019_2936371
crossref_primary_10_1007_s00521_019_04689_6
crossref_primary_10_1049_sil2_12156
crossref_primary_10_1007_s40997_022_00548_3
crossref_primary_10_1088_1361_6501_acc602
crossref_primary_10_1016_j_energy_2023_128255
crossref_primary_10_1007_s00521_021_06849_z
crossref_primary_10_1016_j_wear_2022_204606
crossref_primary_10_1007_s00521_021_06780_3
crossref_primary_10_1007_s10586_020_03050_0
crossref_primary_10_3390_nano15141112
crossref_primary_10_1007_s00521_021_05997_6
crossref_primary_10_7717_peerj_cs_1396
crossref_primary_10_1007_s10462_019_09719_2
crossref_primary_10_1109_TEVC_2021_3079985
crossref_primary_10_1007_s10772_019_09639_0
crossref_primary_10_1186_s10033_020_00443_5
crossref_primary_10_1016_j_apnum_2022_07_008
crossref_primary_10_1017_S0022029925101416
crossref_primary_10_3233_JIFS_171307
crossref_primary_10_1016_j_engappai_2022_105024
crossref_primary_10_1016_j_asoc_2018_06_010
crossref_primary_10_1007_s10462_021_09992_0
crossref_primary_10_1016_j_neucom_2019_06_033
crossref_primary_10_1109_TEVC_2022_3171052
crossref_primary_10_1186_s40703_025_00232_w
crossref_primary_10_1016_j_neucom_2019_03_097
crossref_primary_10_1016_j_cegh_2018_12_004
crossref_primary_10_1016_j_asoc_2019_106053
crossref_primary_10_1007_s00500_019_03858_y
crossref_primary_10_1007_s11063_022_11055_6
crossref_primary_10_1016_j_engappai_2017_09_002
crossref_primary_10_1109_TFUZZ_2020_2973123
crossref_primary_10_1007_s11075_022_01425_5
crossref_primary_10_1007_s10489_022_04299_1
crossref_primary_10_1007_s11047_018_9674_1
crossref_primary_10_1007_s40314_022_01962_8
crossref_primary_10_17780_ksujes_1561429
crossref_primary_10_1080_08839514_2022_2031815
crossref_primary_10_1016_j_asoc_2020_106799
crossref_primary_10_1007_s00371_020_01834_4
crossref_primary_10_1007_s11042_023_15889_7
crossref_primary_10_1016_j_apacoust_2020_107573
crossref_primary_10_3390_informatics6010001
crossref_primary_10_1007_s13042_018_0811_z
crossref_primary_10_1016_j_egyr_2022_09_188
crossref_primary_10_1016_j_cmpb_2021_106432
crossref_primary_10_1016_j_ins_2021_03_060
crossref_primary_10_3390_electronics10212689
crossref_primary_10_1016_j_asoc_2023_110412
crossref_primary_10_3389_ffutr_2021_710330
crossref_primary_10_3390_bioengineering10060639
crossref_primary_10_1049_rpg2_12471
crossref_primary_10_1007_s00500_024_09840_7
crossref_primary_10_1093_comjnl_bxaa029
crossref_primary_10_1016_j_engappai_2023_106675
crossref_primary_10_1155_2020_5787642
crossref_primary_10_1109_TII_2019_2938884
crossref_primary_10_1007_s00500_018_03683_9
crossref_primary_10_1155_2019_5012313
crossref_primary_10_1007_s12530_019_09294_5
crossref_primary_10_1016_j_compeleceng_2018_04_012
crossref_primary_10_1080_0305215X_2019_1595611
crossref_primary_10_1109_ACCESS_2020_3000322
crossref_primary_10_1007_s11042_020_09268_9
crossref_primary_10_1016_j_eswa_2021_115153
crossref_primary_10_1109_ACCESS_2023_3299296
crossref_primary_10_1109_TNNLS_2020_3026114
crossref_primary_10_1063_5_0221924
crossref_primary_10_1002_cpe_6988
crossref_primary_10_1016_j_neucom_2018_05_040
crossref_primary_10_1109_TSMC_2019_2897330
Cites_doi 10.1162/08997660260293319
10.1016/j.neucom.2015.09.116
10.1504/IJDMB.2016.075823
10.1007/BF01589116
10.14311/NNW.2011.21.028
10.1090/S0025-5718-1980-0572855-7
10.1126/science.1127647
10.1016/0004-3702(89)90049-0
10.1007/978-3-642-35289-8_26
10.1016/j.neucom.2017.01.090
10.1109/TCBB.2011.140
10.3389/fnhum.2011.00076
10.1016/j.engappai.2016.01.032
10.5755/j01.eie.23.2.18002
10.1016/j.ins.2010.07.015
10.1016/j.asoc.2007.05.007
10.1016/j.neucom.2016.12.038
10.1016/j.neucom.2016.09.018
10.1016/j.neucom.2016.09.010
10.1016/j.neucom.2015.10.064
10.1016/j.asoc.2016.05.021
10.1007/s10957-012-0107-5
10.1007/s12559-016-9404-x
10.1016/j.asoc.2010.12.001
10.1007/s10898-007-9149-x
10.1007/s12559-016-9396-6
10.1038/nature14539
10.1109/TNN.2002.804317
10.1016/j.ins.2013.08.035
ContentType Journal Article
Copyright 2017 Elsevier B.V.
Copyright_xml – notice: 2017 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.neucom.2017.05.061
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1872-8286
EndPage 526
ExternalDocumentID 10_1016_j_neucom_2017_05_061
S0925231217309487
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
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
AXJTR
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
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
RIG
ROL
RPZ
SDF
SDG
SDP
SES
SPC
SPCBC
SSN
SSV
SSZ
T5K
ZMT
~G-
29N
9DU
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
FEDTE
FGOYB
HLZ
HVGLF
HZ~
R2-
SBC
SEW
WUQ
XPP
~HD
ID FETCH-LOGICAL-c372t-a05a0c6f4d30f4b66099166ac0c1b9c9f13f6e0dae2f1119fbf852954271c0f03
ISICitedReferencesCount 91
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000408183900046&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0925-2312
IngestDate Sat Nov 29 03:02:49 EST 2025
Tue Nov 18 22:23:38 EST 2025
Fri Feb 23 02:30:23 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Deep neural network
Stacked autoencoder network
Artificial bee colony optimization algorithm
L-BFGS
Hybridization
Training strategy
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c372t-a05a0c6f4d30f4b66099166ac0c1b9c9f13f6e0dae2f1119fbf852954271c0f03
ORCID 0000-0001-5810-0643
PageCount 21
ParticipantIDs crossref_primary_10_1016_j_neucom_2017_05_061
crossref_citationtrail_10_1016_j_neucom_2017_05_061
elsevier_sciencedirect_doi_10_1016_j_neucom_2017_05_061
PublicationCentury 2000
PublicationDate 2017-11-29
PublicationDateYYYYMMDD 2017-11-29
PublicationDate_xml – month: 11
  year: 2017
  text: 2017-11-29
  day: 29
PublicationDecade 2010
PublicationTitle Neurocomputing (Amsterdam)
PublicationYear 2017
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Karaboga (bib0032) 2005
Chen, Liu, Zhang, Liang, Suganthan, Qu (bib0050) 2014
Leung, Lam, Ling, Tam (bib0023) 2003; 14
Karaboga, Aslan (bib0039) 2016; 16
Karaboga, Basturk (bib0033) 2007; 39
Basturk, Akay (bib0036) 2012; 155
Hinton (bib0001) 1989; 40
A. Ng, “Sparse autoencoder,” CS294A Lecture Notes, Stanford Univ., Stanford, CA, USA, Tech. Rep., 2011.
Vincent, Larochelle, Bengio, Manzagol (bib0015) 2008
Henson, Wakeman, Litvak, Friston (bib0044) 2011; 5
Recognition of Convex Sets.
Y. Bengio, Practical Recommendations for Gradient-Based Training of Deep Architectures, Springer Berlin Heidelberg, pp. 437–478.
Zhang, Zhang, Chen (bib0028) 2016; 50
Ranzato, Poultney, Chopra, LeCun (bib0025) 2006
Berahas, Nocedal, Takác (bib0031) 2016
Guo, Liu, Oerlemans, Lao, Wu, Lew (bib0013) 2016; 187
Olivetti, Kia, Avesani (bib0045) 2014
Huang, Siniscalchi, Lee (bib0006) 2016; 218
Ngiam, Coates, Lahiri, Prochnow, Le, Ng (bib0019) 2011
Yu, Jia, Xu (bib0008) 2017; 219
Badem, Caliskan, Basturk, Yuksel (bib0010) 2016
Zeng, Wang, Zhang, Alsaadi (bib0017) 2016; 8
DecMeg2014-Decoding the Human Brain.
Basturk, Akay (bib0020) 2013; 253
LeCun, Bengio, Hinton (bib0012) 2015; 521
Nocedal (bib0029) 1980; 35
Akay, Karaboga (bib0040) 2012; 192
.
Akay, Karaboga (bib0035) 2011; 11
Caliskan, Yuksel, Badem, Basturk (bib0047) 2017; 23
Karaboga, Basturk (bib0034) 2008; 8
Bengio, Lamblin, Popovici, Larochelle (bib0004) 2007
Karaboga, Ozturk (bib0022) 2009; 19
Utgoff, Stracuzzi (bib0002) 2002; 14
Zeng, Wang, Li, Du, Liu (bib0016) 2012; 9
Liu, Wang, Liu, Zeng, Liu, Alsaadi (bib0014) 2017; 234
Ozkan, Ozturk, Sunar, Karaboga (bib0021) 2011; 21
Ozturk, Aslan (bib0037) 2016; 14
Hinton, Salakhutdinov (bib0003) 2006; 313
Rectangles and Rectangles-Images Data.
Bengio, LeCun (bib0005) 2007; 34
Basturk, Yuksel, Caliskan, Badem (bib0043) 2017
Badem, Caliskan, Basturk, Yuksel (bib0009) 2016
Wu, Lu, Gao, Zhao, Liu (bib0007) 2016; 175
Liu, Zhang, Wu, Liang, Wang, Teo (bib0041) 2016; 47
Zeng, Zhang, Liu, Liang, Alsaadi (bib0018) 2017; 240
Liu, Nocedal (bib0030) 1989; 45
M. Lichman, UCI Machine Learning Repository, 2013
Karaboga, Aslan (bib0038) 2015; 15
Karaboga, Akay (bib0024) 2009; 214
Zeng, Wang, Zhang, Liu, Alsaadi (bib0011) 2016; 8
Karaboga (10.1016/j.neucom.2017.05.061_bib0038) 2015; 15
Basturk (10.1016/j.neucom.2017.05.061_bib0043) 2017
Bengio (10.1016/j.neucom.2017.05.061_bib0005) 2007; 34
Badem (10.1016/j.neucom.2017.05.061_bib0009) 2016
Guo (10.1016/j.neucom.2017.05.061_bib0013) 2016; 187
10.1016/j.neucom.2017.05.061_bib0048
Berahas (10.1016/j.neucom.2017.05.061_bib0031) 2016
Karaboga (10.1016/j.neucom.2017.05.061_bib0022) 2009; 19
10.1016/j.neucom.2017.05.061_bib0049
Akay (10.1016/j.neucom.2017.05.061_bib0040) 2012; 192
Liu (10.1016/j.neucom.2017.05.061_bib0014) 2017; 234
Liu (10.1016/j.neucom.2017.05.061_bib0041) 2016; 47
Zhang (10.1016/j.neucom.2017.05.061_bib0028) 2016; 50
Bengio (10.1016/j.neucom.2017.05.061_bib0004) 2007
Hinton (10.1016/j.neucom.2017.05.061_bib0003) 2006; 313
Zeng (10.1016/j.neucom.2017.05.061_bib0011) 2016; 8
10.1016/j.neucom.2017.05.061_bib0042
Olivetti (10.1016/j.neucom.2017.05.061_bib0045) 2014
10.1016/j.neucom.2017.05.061_bib0046
Akay (10.1016/j.neucom.2017.05.061_bib0035) 2011; 11
Karaboga (10.1016/j.neucom.2017.05.061_bib0033) 2007; 39
Caliskan (10.1016/j.neucom.2017.05.061_bib0047) 2017; 23
Zeng (10.1016/j.neucom.2017.05.061_bib0017) 2016; 8
Chen (10.1016/j.neucom.2017.05.061_bib0050) 2014
Yu (10.1016/j.neucom.2017.05.061_bib0008) 2017; 219
Utgoff (10.1016/j.neucom.2017.05.061_bib0002) 2002; 14
Henson (10.1016/j.neucom.2017.05.061_bib0044) 2011; 5
Hinton (10.1016/j.neucom.2017.05.061_bib0001) 1989; 40
Basturk (10.1016/j.neucom.2017.05.061_bib0036) 2012; 155
Ngiam (10.1016/j.neucom.2017.05.061_bib0019) 2011
Karaboga (10.1016/j.neucom.2017.05.061_bib0032) 2005
Badem (10.1016/j.neucom.2017.05.061_bib0010) 2016
Wu (10.1016/j.neucom.2017.05.061_bib0007) 2016; 175
10.1016/j.neucom.2017.05.061_bib0026
Karaboga (10.1016/j.neucom.2017.05.061_bib0039) 2016; 16
Zeng (10.1016/j.neucom.2017.05.061_bib0018) 2017; 240
10.1016/j.neucom.2017.05.061_bib0027
Ozturk (10.1016/j.neucom.2017.05.061_bib0037) 2016; 14
Zeng (10.1016/j.neucom.2017.05.061_bib0016) 2012; 9
Leung (10.1016/j.neucom.2017.05.061_bib0023) 2003; 14
Ranzato (10.1016/j.neucom.2017.05.061_bib0025) 2006
Vincent (10.1016/j.neucom.2017.05.061_bib0015) 2008
LeCun (10.1016/j.neucom.2017.05.061_bib0012) 2015; 521
Nocedal (10.1016/j.neucom.2017.05.061_bib0029) 1980; 35
Basturk (10.1016/j.neucom.2017.05.061_bib0020) 2013; 253
Karaboga (10.1016/j.neucom.2017.05.061_bib0034) 2008; 8
Huang (10.1016/j.neucom.2017.05.061_bib0006) 2016; 218
Liu (10.1016/j.neucom.2017.05.061_bib0030) 1989; 45
Ozkan (10.1016/j.neucom.2017.05.061_bib0021) 2011; 21
Karaboga (10.1016/j.neucom.2017.05.061_bib0024) 2009; 214
References_xml – start-page: 1137
  year: 2006
  end-page: 1144
  ident: bib0025
  article-title: Efficient learning of sparse representations with an energy-based model
  publication-title: Advances in Neural Information Processing Systems
– volume: 14
  start-page: 2497
  year: 2002
  end-page: 2529
  ident: bib0002
  article-title: Many-Layered Learning
  publication-title: Neural Comput.
– volume: 8
  start-page: 684
  year: 2016
  end-page: 692
  ident: bib0011
  article-title: Deep belief networks for quantitative analysis of a gold immunochromatographic strip
  publication-title: Cognitive Comput.
– start-page: 265
  year: 2011
  end-page: 272
  ident: bib0019
  article-title: On optimization methods for deep learning
  publication-title: Proceedings of the 28th International Conference on Machine Learning (ICML-11)
– volume: 21
  start-page: 473
  year: 2011
  end-page: 492
  ident: bib0021
  article-title: The artificial bee colony algorithm in training artificial neural network for oil spill detection
  publication-title: Neural Netw. World
– volume: 11
  start-page: 3021
  year: 2011
  end-page: 3031
  ident: bib0035
  article-title: A modified artificial bee colony (ABC) algorithm for constrained optimization problems
  publication-title: Appl. Soft Comput.
– reference: Rectangles and Rectangles-Images Data.
– reference: A. Ng, “Sparse autoencoder,” CS294A Lecture Notes, Stanford Univ., Stanford, CA, USA, Tech. Rep., 2011.
– reference: Recognition of Convex Sets.
– volume: 14
  start-page: 332
  year: 2016
  end-page: 353
  ident: bib0037
  article-title: A new artificial bee colony algorithm to solve the multiple sequence alignment problem
  publication-title: Int. J. Data Mining Bioinform.
– volume: 8
  start-page: 143
  year: 2016
  end-page: 152
  ident: bib0017
  article-title: A novel switching delayed PSO algorithm for estimating unknown parameters of lateral flow immunoassay
  publication-title: Cognitive Comput.
– reference: DecMeg2014-Decoding the Human Brain.
– volume: 214
  start-page: 108
  year: 2009
  end-page: 132
  ident: bib0024
  article-title: A comparative study of artificial bee colony algorithm
  publication-title: Appl. Math. Comput.
– start-page: 153
  year: 2007
  end-page: 160
  ident: bib0004
  article-title: Greedy Layer-Wise Training of Deep Networks
  publication-title: Proceedings of 19th the Advances in Neural Information Processing Systems
– volume: 219
  start-page: 88
  year: 2017
  end-page: 98
  ident: bib0008
  article-title: Convolutional neural networks for hyperspectral image classification
  publication-title: Neurocomputing
– reference: Y. Bengio, Practical Recommendations for Gradient-Based Training of Deep Architectures, Springer Berlin Heidelberg, pp. 437–478.
– volume: 8
  start-page: 687
  year: 2008
  end-page: 697
  ident: bib0034
  article-title: On the performance of artificial bee colony (ABC) algorithm
  publication-title: Appl. Soft Comput.
– volume: 45
  start-page: 503
  year: 1989
  end-page: 528
  ident: bib0030
  article-title: On the limited memory BFGS method for large scale optimization
  publication-title: Math. Progr.
– volume: 155
  start-page: 1095
  year: 2012
  end-page: 1104
  ident: bib0036
  article-title: Parallel implementation of synchronous type artificial bee colony algorithm for global optimization
  publication-title: J. Optim. Theory Appl.
– volume: 521
  start-page: 436
  year: 2015
  end-page: 444
  ident: bib0012
  article-title: Deep learning
  publication-title: Nature
– volume: 39
  start-page: 459
  year: 2007
  end-page: 471
  ident: bib0033
  article-title: A powerful and efficient algorithm for numerical function optimization: artificial Bee colony (ABC) algorithm
  publication-title: Global Optim.
– year: 2005
  ident: bib0032
  article-title: An idea based on honey bee swarm for numerical optimization
  publication-title: Technical Report-TR06
– volume: 34
  start-page: 1
  year: 2007
  end-page: 41
  ident: bib0005
  article-title: Scaling learning algorithms towards AI
  publication-title: Large-Scale Kernel Mach.
– volume: 35
  start-page: 773
  year: 1980
  end-page: 782
  ident: bib0029
  article-title: Updating Quasi-Newton Matrices with Limited Storage
  publication-title: Math. Comput.
– reference: M. Lichman, UCI Machine Learning Repository, 2013,
– start-page: 370
  year: 2016
  end-page: 373
  ident: bib0010
  article-title: Classification of human activity by using a stacked autoencoder
  publication-title: Proceedings of Medical Technologies National Conference (TIPTEKNO)
– volume: 5
  start-page: 1
  year: 2011
  end-page: 16
  ident: bib0044
  article-title: A parametric empirical bayesian framework for the eeg/meg inverse problem: generative models for multi-subject and multi-modal integration
  publication-title: Frontiers Human Neurosci.
– start-page: 1
  year: 2014
  end-page: 4
  ident: bib0045
  article-title: meg decoding across subjects
  publication-title: Proceedings of the International Workshop on Pattern Recognition in Neuroimaging
– volume: 19
  start-page: 279
  year: 2009
  end-page: 292
  ident: bib0022
  article-title: Neural networks training by artificial bee colony algorithm on pattern classification
  publication-title: Neural Netw. World
– volume: 14
  start-page: 79
  year: 2003
  end-page: 88
  ident: bib0023
  article-title: Tuning of the structure and parameters of a neural network using an improved genetic algorithm
  publication-title: IEEE Trans. Neural Netw.
– year: 2017
  ident: bib0043
  article-title: Deep Neural Network Classifier for Hand Movement Prediction
  publication-title: Proceedings of the IEEE 25th Signal Processing and Communications Applications Conference SIU
– volume: 313
  start-page: 504
  year: 2006
  end-page: 507
  ident: bib0003
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: Science
– start-page: 1055
  year: 2016
  end-page: 1063
  ident: bib0031
  article-title: A multi-batch L-BFGS method for machine learning
  publication-title: Advances in Neural Information Processing Systems
– volume: 47
  start-page: 281
  year: 2016
  end-page: 294
  ident: bib0041
  article-title: A hybrid approach to constrained global optimization
  publication-title: Appl. Soft Comput.
– year: 2014
  ident: bib0050
  article-title: Problem definitions and evaluation criteria for CEC 2015 special session on bound constrained single-objective computationally expensive numerical optimization
  publication-title: Technical Report
– start-page: 1096
  year: 2008
  end-page: 1103
  ident: bib0015
  article-title: Extracting and composing robust features with denoising autoencoders
  publication-title: Proceedings of the 25th International Conference on Machine Learning
– volume: 187
  start-page: 27
  year: 2016
  end-page: 48
  ident: bib0013
  article-title: Deep learning for visual understanding: a review
  publication-title: Neurocomputing
– volume: 50
  start-page: 245
  year: 2016
  end-page: 255
  ident: bib0028
  article-title: Deep neural network for halftone image classification based on sparse auto-encoder
  publication-title: Eng. Appl. Artif. Intel.
– volume: 15
  start-page: 1
  year: 2015
  end-page: 11
  ident: bib0038
  article-title: A discrete artificial bee colony algorithm for detecting transcription factor binding sites in dna sequences
  publication-title: Genetics Molecular Res. GMR
– volume: 16
  start-page: 2055
  year: 2016
  end-page: 2064
  ident: bib0039
  article-title: Best supported emigrant creation for parallel implementation of artificial Bee colony algorithm
  publication-title: IU-J. Electr. Electron. Eng.
– volume: 253
  start-page: 34
  year: 2013
  end-page: 55
  ident: bib0020
  article-title: Performance analysis of the coarse-Grained Parallel model of the artificial bee colony algorithm
  publication-title: Inform. Sci.
– volume: 218
  start-page: 448
  year: 2016
  end-page: 459
  ident: bib0006
  article-title: A unified approach to transfer learning of deep neural networks with applications to speaker adaptation in automatic speech recognition
  publication-title: Neurocomputing
– volume: 23
  start-page: 63
  year: 2017
  end-page: 67
  ident: bib0047
  article-title: A deep neural network classifier for decoding human brain activity based on magnetoencephalography
  publication-title: Elektronika ir Elektrotechnika
– volume: 192
  start-page: 120
  year: 2012
  end-page: 142
  ident: bib0040
  article-title: A modified artificial bee colony algorithm for real-parameter optimization
  publication-title: Inform. Sci.
– volume: 9
  start-page: 321
  year: 2012
  end-page: 329
  ident: bib0016
  article-title: A hybrid EKF and switching PSO algorithm for joint state and parameter estimation of lateral flow immunoassay models
  publication-title: IEEE/ACM Trans. Comput. Biol. Bioinform.
– volume: 240
  start-page: 175
  year: 2017
  end-page: 182
  ident: bib0018
  article-title: A switching delayed PSO optimized extreme learning machine for short-term load forecasting
  publication-title: Neurocomputing
– reference: .
– start-page: 499
  year: 2016
  end-page: 502
  ident: bib0009
  article-title: Classification and diagnosis of the Parkinson disease by stacked autoencoder
  publication-title: Proceedings of 9th National Conference on Electrical and Electronics Engineering, ELECO
– volume: 175
  start-page: 310
  year: 2016
  end-page: 323
  ident: bib0007
  article-title: Regional deep learning model for visual tracking
  publication-title: Neurocomputing
– volume: 234
  start-page: 11
  year: 2017
  end-page: 26
  ident: bib0014
  article-title: A survey of deep neural network architectures and their applications
  publication-title: Neurocomputing
– volume: 40
  start-page: 185
  year: 1989
  end-page: 234
  ident: bib0001
  article-title: Connectionist Learning Procedures
  publication-title: Artif. Intel.
– volume: 14
  start-page: 2497
  issue: 10
  year: 2002
  ident: 10.1016/j.neucom.2017.05.061_bib0002
  article-title: Many-Layered Learning
  publication-title: Neural Comput.
  doi: 10.1162/08997660260293319
– volume: 187
  start-page: 27
  year: 2016
  ident: 10.1016/j.neucom.2017.05.061_bib0013
  article-title: Deep learning for visual understanding: a review
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2015.09.116
– volume: 14
  start-page: 332
  issue: 4
  year: 2016
  ident: 10.1016/j.neucom.2017.05.061_bib0037
  article-title: A new artificial bee colony algorithm to solve the multiple sequence alignment problem
  publication-title: Int. J. Data Mining Bioinform.
  doi: 10.1504/IJDMB.2016.075823
– volume: 45
  start-page: 503
  issue: 1
  year: 1989
  ident: 10.1016/j.neucom.2017.05.061_bib0030
  article-title: On the limited memory BFGS method for large scale optimization
  publication-title: Math. Progr.
  doi: 10.1007/BF01589116
– volume: 21
  start-page: 473
  issue: 6
  year: 2011
  ident: 10.1016/j.neucom.2017.05.061_bib0021
  article-title: The artificial bee colony algorithm in training artificial neural network for oil spill detection
  publication-title: Neural Netw. World
  doi: 10.14311/NNW.2011.21.028
– volume: 35
  start-page: 773
  issue: 151
  year: 1980
  ident: 10.1016/j.neucom.2017.05.061_bib0029
  article-title: Updating Quasi-Newton Matrices with Limited Storage
  publication-title: Math. Comput.
  doi: 10.1090/S0025-5718-1980-0572855-7
– volume: 313
  start-page: 504
  issue: 5786
  year: 2006
  ident: 10.1016/j.neucom.2017.05.061_bib0003
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: Science
  doi: 10.1126/science.1127647
– volume: 40
  start-page: 185
  issue: 1
  year: 1989
  ident: 10.1016/j.neucom.2017.05.061_bib0001
  article-title: Connectionist Learning Procedures
  publication-title: Artif. Intel.
  doi: 10.1016/0004-3702(89)90049-0
– ident: 10.1016/j.neucom.2017.05.061_bib0027
  doi: 10.1007/978-3-642-35289-8_26
– volume: 240
  start-page: 175
  year: 2017
  ident: 10.1016/j.neucom.2017.05.061_bib0018
  article-title: A switching delayed PSO optimized extreme learning machine for short-term load forecasting
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2017.01.090
– volume: 9
  start-page: 321
  issue: 2
  year: 2012
  ident: 10.1016/j.neucom.2017.05.061_bib0016
  article-title: A hybrid EKF and switching PSO algorithm for joint state and parameter estimation of lateral flow immunoassay models
  publication-title: IEEE/ACM Trans. Comput. Biol. Bioinform.
  doi: 10.1109/TCBB.2011.140
– volume: 5
  start-page: 1
  year: 2011
  ident: 10.1016/j.neucom.2017.05.061_bib0044
  article-title: A parametric empirical bayesian framework for the eeg/meg inverse problem: generative models for multi-subject and multi-modal integration
  publication-title: Frontiers Human Neurosci.
  doi: 10.3389/fnhum.2011.00076
– year: 2017
  ident: 10.1016/j.neucom.2017.05.061_bib0043
  article-title: Deep Neural Network Classifier for Hand Movement Prediction
– volume: 19
  start-page: 279
  issue: 3
  year: 2009
  ident: 10.1016/j.neucom.2017.05.061_bib0022
  article-title: Neural networks training by artificial bee colony algorithm on pattern classification
  publication-title: Neural Netw. World
– start-page: 1137
  year: 2006
  ident: 10.1016/j.neucom.2017.05.061_bib0025
  article-title: Efficient learning of sparse representations with an energy-based model
– ident: 10.1016/j.neucom.2017.05.061_bib0026
– ident: 10.1016/j.neucom.2017.05.061_bib0049
– volume: 50
  start-page: 245
  year: 2016
  ident: 10.1016/j.neucom.2017.05.061_bib0028
  article-title: Deep neural network for halftone image classification based on sparse auto-encoder
  publication-title: Eng. Appl. Artif. Intel.
  doi: 10.1016/j.engappai.2016.01.032
– volume: 15
  start-page: 1
  issue: 2
  year: 2015
  ident: 10.1016/j.neucom.2017.05.061_bib0038
  article-title: A discrete artificial bee colony algorithm for detecting transcription factor binding sites in dna sequences
  publication-title: Genetics Molecular Res. GMR
– start-page: 499
  year: 2016
  ident: 10.1016/j.neucom.2017.05.061_bib0009
  article-title: Classification and diagnosis of the Parkinson disease by stacked autoencoder
– start-page: 1055
  year: 2016
  ident: 10.1016/j.neucom.2017.05.061_bib0031
  article-title: A multi-batch L-BFGS method for machine learning
– volume: 23
  start-page: 63
  issue: 2
  year: 2017
  ident: 10.1016/j.neucom.2017.05.061_bib0047
  article-title: A deep neural network classifier for decoding human brain activity based on magnetoencephalography
  publication-title: Elektronika ir Elektrotechnika
  doi: 10.5755/j01.eie.23.2.18002
– start-page: 1
  year: 2014
  ident: 10.1016/j.neucom.2017.05.061_bib0045
  article-title: meg decoding across subjects
– volume: 192
  start-page: 120
  year: 2012
  ident: 10.1016/j.neucom.2017.05.061_bib0040
  article-title: A modified artificial bee colony algorithm for real-parameter optimization
  publication-title: Inform. Sci.
  doi: 10.1016/j.ins.2010.07.015
– volume: 8
  start-page: 687
  issue: 1
  year: 2008
  ident: 10.1016/j.neucom.2017.05.061_bib0034
  article-title: On the performance of artificial bee colony (ABC) algorithm
  publication-title: Appl. Soft Comput.
  doi: 10.1016/j.asoc.2007.05.007
– volume: 234
  start-page: 11
  year: 2017
  ident: 10.1016/j.neucom.2017.05.061_bib0014
  article-title: A survey of deep neural network architectures and their applications
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2016.12.038
– ident: 10.1016/j.neucom.2017.05.061_bib0048
– volume: 218
  start-page: 448
  year: 2016
  ident: 10.1016/j.neucom.2017.05.061_bib0006
  article-title: A unified approach to transfer learning of deep neural networks with applications to speaker adaptation in automatic speech recognition
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2016.09.018
– volume: 219
  start-page: 88
  year: 2017
  ident: 10.1016/j.neucom.2017.05.061_bib0008
  article-title: Convolutional neural networks for hyperspectral image classification
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2016.09.010
– volume: 175
  start-page: 310
  year: 2016
  ident: 10.1016/j.neucom.2017.05.061_bib0007
  article-title: Regional deep learning model for visual tracking
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2015.10.064
– volume: 47
  start-page: 281
  year: 2016
  ident: 10.1016/j.neucom.2017.05.061_bib0041
  article-title: A hybrid approach to constrained global optimization
  publication-title: Appl. Soft Comput.
  doi: 10.1016/j.asoc.2016.05.021
– year: 2014
  ident: 10.1016/j.neucom.2017.05.061_bib0050
  article-title: Problem definitions and evaluation criteria for CEC 2015 special session on bound constrained single-objective computationally expensive numerical optimization
– start-page: 370
  year: 2016
  ident: 10.1016/j.neucom.2017.05.061_bib0010
  article-title: Classification of human activity by using a stacked autoencoder
– volume: 155
  start-page: 1095
  issue: 3
  year: 2012
  ident: 10.1016/j.neucom.2017.05.061_bib0036
  article-title: Parallel implementation of synchronous type artificial bee colony algorithm for global optimization
  publication-title: J. Optim. Theory Appl.
  doi: 10.1007/s10957-012-0107-5
– volume: 214
  start-page: 108
  issue: 1
  year: 2009
  ident: 10.1016/j.neucom.2017.05.061_bib0024
  article-title: A comparative study of artificial bee colony algorithm
  publication-title: Appl. Math. Comput.
– volume: 16
  start-page: 2055
  issue: 2
  year: 2016
  ident: 10.1016/j.neucom.2017.05.061_bib0039
  article-title: Best supported emigrant creation for parallel implementation of artificial Bee colony algorithm
  publication-title: IU-J. Electr. Electron. Eng.
– start-page: 1096
  year: 2008
  ident: 10.1016/j.neucom.2017.05.061_bib0015
  article-title: Extracting and composing robust features with denoising autoencoders
– ident: 10.1016/j.neucom.2017.05.061_bib0042
– start-page: 153
  year: 2007
  ident: 10.1016/j.neucom.2017.05.061_bib0004
  article-title: Greedy Layer-Wise Training of Deep Networks
– volume: 34
  start-page: 1
  issue: 5
  year: 2007
  ident: 10.1016/j.neucom.2017.05.061_bib0005
  article-title: Scaling learning algorithms towards AI
  publication-title: Large-Scale Kernel Mach.
– volume: 8
  start-page: 684
  issue: 4
  year: 2016
  ident: 10.1016/j.neucom.2017.05.061_bib0011
  article-title: Deep belief networks for quantitative analysis of a gold immunochromatographic strip
  publication-title: Cognitive Comput.
  doi: 10.1007/s12559-016-9404-x
– volume: 11
  start-page: 3021
  issue: 3
  year: 2011
  ident: 10.1016/j.neucom.2017.05.061_bib0035
  article-title: A modified artificial bee colony (ABC) algorithm for constrained optimization problems
  publication-title: Appl. Soft Comput.
  doi: 10.1016/j.asoc.2010.12.001
– volume: 39
  start-page: 459
  issue: 3
  year: 2007
  ident: 10.1016/j.neucom.2017.05.061_bib0033
  article-title: A powerful and efficient algorithm for numerical function optimization: artificial Bee colony (ABC) algorithm
  publication-title: Global Optim.
  doi: 10.1007/s10898-007-9149-x
– volume: 8
  start-page: 143
  issue: 2
  year: 2016
  ident: 10.1016/j.neucom.2017.05.061_bib0017
  article-title: A novel switching delayed PSO algorithm for estimating unknown parameters of lateral flow immunoassay
  publication-title: Cognitive Comput.
  doi: 10.1007/s12559-016-9396-6
– volume: 521
  start-page: 436
  issue: 7553
  year: 2015
  ident: 10.1016/j.neucom.2017.05.061_bib0012
  article-title: Deep learning
  publication-title: Nature
  doi: 10.1038/nature14539
– volume: 14
  start-page: 79
  issue: 1
  year: 2003
  ident: 10.1016/j.neucom.2017.05.061_bib0023
  article-title: Tuning of the structure and parameters of a neural network using an improved genetic algorithm
  publication-title: IEEE Trans. Neural Netw.
  doi: 10.1109/TNN.2002.804317
– start-page: 265
  year: 2011
  ident: 10.1016/j.neucom.2017.05.061_bib0019
  article-title: On optimization methods for deep learning
– ident: 10.1016/j.neucom.2017.05.061_bib0046
– volume: 253
  start-page: 34
  year: 2013
  ident: 10.1016/j.neucom.2017.05.061_bib0020
  article-title: Performance analysis of the coarse-Grained Parallel model of the artificial bee colony algorithm
  publication-title: Inform. Sci.
  doi: 10.1016/j.ins.2013.08.035
– year: 2005
  ident: 10.1016/j.neucom.2017.05.061_bib0032
  article-title: An idea based on honey bee swarm for numerical optimization
SSID ssj0017129
Score 2.5012867
Snippet Working up with deep learning techniques requires profound understanding of the mechanisms underlying the optimization of the internal parameters of complex...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 506
SubjectTerms Artificial bee colony optimization algorithm
Deep learning
Deep neural network
Hybridization
L-BFGS
Stacked autoencoder network
Training strategy
Title A new efficient training strategy for deep neural networks by hybridization of artificial bee colony and limited–memory BFGS optimization algorithms
URI https://dx.doi.org/10.1016/j.neucom.2017.05.061
Volume 266
WOSCitedRecordID wos000408183900046&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-8286
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017129
  issn: 0925-2312
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3JjtNAEG1FGQ5c2BHDpjpwi4za7f3ooAyLxAiJQQony27bZHWiOBlNbvwDEt_GmS-hyt3tJAwamAMXK7LittP10lVdfvWKsRdR6NocF19LYOxhuXbgWKGQpSXRdToi9PxMuk2zieD0NBwOow-dzg9TC3M-C6oqvLiIlv_V1HgOjU2ls9cwdzsonsDPaHQ8otnx-E-Gj6lLOPE0xk2tY9sEolcrIVrF0MyLYtkjMUs0UaWo4DWFoqMtlXDp4syGJLBq2ESUWM8KorbPFpXSbJqp2ihDl3DmRNrd9vonrz_2FrgSzc0o6ezLYjVej7Qw-sQIRm3QeTZNJXS6Ip6TakNOEG3TE32i7zf-Md2jD_XTGl3lVFXoLHcEY6o0q6cqpxtnOW6vd-nuz5tprSgJ74vRvFj3BnOtOq6THuhIbdvSt9bZS-FZGJoeLOTC31-KPe7veXVP1eVfchgqdzF5iRNO7CG6V6PkqhTiD_W5f_ObLZvREOUmiRoloVES7iWc9uVHIkDYd9lR_HYwfNe-4QpsoXQg9Q8xZZ0N9_Dy0_w5bNoLhc7usFt6DwOxwt5d1imqe-y26Q8C2l3cZ99jQChCC0UwUAQDRUAoAkERFBTBQBGyLRxAERYl7KAICEVQUASEImgo_vz6TYEQCISwD0LYgfAB-3QyOHv1xtJ9QCzpBGJtpdxLufRLN3d46Wa-z2lT46eSSzuLZFTaTukXPE8LUaLrjsqsDJv31yKwJS-585B1q0VVPGIQZiEpWApfBrabU5eZQBKTgFQmC9_NjpljpjmRWiSf5maWXGXkY2a1Vy2VSMxfvh8YCyY60FUBbIKwvPLKx9e80xN2c_f3ecq669WmeMZuyPP1uF4915j8BYRM0tY
linkProvider Elsevier
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+new+efficient+training+strategy+for+deep+neural+networks+by+hybridization+of+artificial+bee+colony+and+limited%E2%80%93memory+BFGS+optimization+algorithms&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Badem%2C+Hasan&rft.au=Basturk%2C+Alper&rft.au=Caliskan%2C+Abdullah&rft.au=Yuksel%2C+Mehmet+Emin&rft.date=2017-11-29&rft.issn=0925-2312&rft.volume=266&rft.spage=506&rft.epage=526&rft_id=info:doi/10.1016%2Fj.neucom.2017.05.061&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_neucom_2017_05_061
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