Deterministic annealing for clustering, compression, classification, regression, and related optimization problems

The deterministic annealing approach to clustering and its extensions has demonstrated substantial performance improvement over standard supervised and unsupervised learning methods in a variety of important applications including compression, estimation, pattern recognition and classification, and...

Full description

Saved in:
Bibliographic Details
Published inProceedings of the IEEE Vol. 86; no. 11; pp. 2210 - 2239
Main Author Rose, K.
Format Journal Article
LanguageEnglish
Published IEEE 01.11.1998
Subjects
Online AccessGet full text
ISSN0018-9219
DOI10.1109/5.726788

Cover

Abstract The deterministic annealing approach to clustering and its extensions has demonstrated substantial performance improvement over standard supervised and unsupervised learning methods in a variety of important applications including compression, estimation, pattern recognition and classification, and statistical regression. The application-specific cost is minimized subject to a constraint on the randomness of the solution, which is gradually lowered. We emphasize the intuition gained from analogy to statistical physics. Alternatively the method is derived within rate-distortion theory, where the annealing process is equivalent to computation of Shannon's rate-distortion function, and the annealing temperature is inversely proportional to the slope of the curve. The basic algorithm is extended by incorporating structural constraints to allow optimization of numerous popular structures including vector quantizers, decision trees, multilayer perceptrons, radial basis functions, and mixtures of experts.
AbstractList The deterministic annealing approach to clustering and its extensions has demonstrated substantial performance improvement over standard supervised and unsupervised learning methods in a variety of important applications including compression, estimation, pattern recognition and classification, and statistical regression. The application-specific cost is minimized subject to a constraint on the randomness of the solution, which is gradually lowered. We emphasize the intuition gained from analogy to statistical physics. Alternatively the method is derived within rate-distortion theory, where the annealing process is equivalent to computation of Shannon's rate-distortion function, and the annealing temperature is inversely proportional to the slope of the curve. The basic algorithm is extended by incorporating structural constraints to allow optimization of numerous popular structures including vector quantizers, decision trees, multilayer perceptrons, radial basis functions, and mixtures of experts.
Author Rose, K.
Author_xml – sequence: 1
  givenname: K.
  surname: Rose
  fullname: Rose, K.
  organization: Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
BookMark eNptkDFPwzAQhT0UibYgMTNlZCDlnDSJO6JCAakSC8yRczlXRo4d2WaAX09Iqg6I6e7Te-90egs2s84SY1ccVpzD5q5YVVlZCTFjcwAu0k3GN-dsEcIHAORFmc-Zf6BIvtNWh6gxkdaSNNoeEuV8guYzDOqAtwm6rvcUgnZ2ACOHTWmUcWRPh5MmbTuwkZHaxPVRd_p7dCW9d42hLlywMyVNoMvjXLL33ePb9jndvz69bO_3KeYcYtrICtZAHJqcy7IsVFm1CCSzdUOZFBWhEkCqBdHwlhSCqhpoOQpCKBGKfMluprvoXQieVN173Un_VXOof_upi3rqZ7Cu_lhRx_Hr6KU2_wWup4AmotPdo_gD7st3ng
CODEN IEEPAD
CitedBy_id crossref_primary_10_1007_s12064_011_0142_z
crossref_primary_10_1016_S0370_2693_02_02475_9
crossref_primary_10_1186_1471_2105_12_358
crossref_primary_10_1109_TIT_2009_2037045
crossref_primary_10_1007_s10115_006_0009_7
crossref_primary_10_1371_journal_pone_0056259
crossref_primary_10_1007_s11634_009_0052_9
crossref_primary_10_1016_S0165_1684_01_00048_2
crossref_primary_10_1002_cpe_1365
crossref_primary_10_1016_j_procs_2019_01_017
crossref_primary_10_1109_TCNS_2020_2995831
crossref_primary_10_1073_pnas_96_12_6745
crossref_primary_10_1109_TGRS_2006_890557
crossref_primary_10_1109_TCSVT_2014_2302516
crossref_primary_10_1109_TIP_2021_3134454
crossref_primary_10_1109_TPDS_2014_2355205
crossref_primary_10_29252_jgit_4_3_57
crossref_primary_10_2139_ssrn_3448703
crossref_primary_10_3156_jsoft_17_392
crossref_primary_10_1186_1471_2164_13_S1_S6
crossref_primary_10_1051_epjconf_201715000001
crossref_primary_10_1109_RBME_2009_2034981
crossref_primary_10_1109_ACCESS_2024_3434655
crossref_primary_10_1007_s11263_014_0707_7
crossref_primary_10_1029_2017WR021993
crossref_primary_10_1109_TSP_2002_1003069
crossref_primary_10_1109_TFUZZ_2023_3345874
crossref_primary_10_1051_epjconf_202227409002
crossref_primary_10_1007_s00138_016_0772_8
crossref_primary_10_1109_TNNLS_2015_2411287
crossref_primary_10_1016_j_nima_2010_01_030
crossref_primary_10_1007_JHEP06_2013_081
crossref_primary_10_1523_JNEUROSCI_1261_06_2007
crossref_primary_10_1109_TNN_2005_845141
crossref_primary_10_1002_asi_23216
crossref_primary_10_24857_rgsa_v19n1_037
crossref_primary_10_1142_S0218213009000263
crossref_primary_10_1145_3130800_3130845
crossref_primary_10_1016_j_neucom_2010_07_015
crossref_primary_10_1162_neco_2006_18_8_1739
crossref_primary_10_3923_itj_2010_1022_1030
crossref_primary_10_4236_jsea_2017_107033
crossref_primary_10_1109_TSP_2009_2037664
crossref_primary_10_1016_j_patrec_2022_05_019
crossref_primary_10_1109_34_990138
crossref_primary_10_1109_TSP_2002_806582
crossref_primary_10_1109_TIT_2023_3329618
crossref_primary_10_1016_j_patcog_2007_06_014
crossref_primary_10_1109_TNNLS_2017_2682179
crossref_primary_10_1016_j_camwa_2007_07_019
crossref_primary_10_1016_j_compeleceng_2024_109693
crossref_primary_10_1109_89_902278
crossref_primary_10_1109_TSP_2016_2585123
crossref_primary_10_1016_j_datak_2006_07_006
crossref_primary_10_1109_34_824819
crossref_primary_10_1109_TCST_2010_2053036
crossref_primary_10_1016_j_physletb_2015_07_053
crossref_primary_10_1109_TKDE_2012_27
crossref_primary_10_1109_TAC_2013_2292726
crossref_primary_10_1109_TAC_2014_2319473
crossref_primary_10_1109_TASL_2010_2090146
crossref_primary_10_1002_widm_1258
crossref_primary_10_3724_SP_J_1001_2008_02276
crossref_primary_10_1016_j_jcp_2007_04_012
crossref_primary_10_1016_j_epsl_2012_10_032
crossref_primary_10_1007_s13721_022_00365_3
crossref_primary_10_1145_980972_980983
crossref_primary_10_1162_089976605774320548
crossref_primary_10_1007_s10994_011_5247_6
crossref_primary_10_1016_j_camwa_2011_07_005
crossref_primary_10_1016_j_ifacol_2023_10_851
crossref_primary_10_1145_2663352
crossref_primary_10_1093_bioinformatics_btt632
crossref_primary_10_1109_TNNLS_2013_2294459
crossref_primary_10_1162_08997660151134334
crossref_primary_10_1016_j_dsp_2020_102905
crossref_primary_10_1016_j_patcog_2006_12_028
crossref_primary_10_1007_BF02916729
crossref_primary_10_20965_jaciii_2018_p0666
crossref_primary_10_1109_TITB_2009_2039644
crossref_primary_10_1016_j_artmed_2014_01_003
crossref_primary_10_1016_j_neunet_2004_06_012
crossref_primary_10_1109_TNN_2004_824416
crossref_primary_10_1109_TPAMI_2010_85
crossref_primary_10_1142_S0218202512300037
crossref_primary_10_1145_3084465
crossref_primary_10_1016_j_physletb_2004_09_024
crossref_primary_10_1109_TMI_2010_2086065
crossref_primary_10_1016_j_scitotenv_2023_169671
crossref_primary_10_1080_27660400_2024_2373046
crossref_primary_10_1063_1_3489885
crossref_primary_10_1016_j_neucom_2010_08_016
crossref_primary_10_1016_j_cag_2012_12_007
crossref_primary_10_1109_TPAMI_2005_160
crossref_primary_10_1109_34_888716
crossref_primary_10_1111_j_1755_0998_2010_02902_x
crossref_primary_10_1007_JHEP05_2019_201
crossref_primary_10_1016_j_physleta_2005_11_068
crossref_primary_10_1080_01691864_2013_871578
crossref_primary_10_1109_TIT_2014_2361532
crossref_primary_10_2478_cait_2018_0030
crossref_primary_10_34133_2022_9763198
crossref_primary_10_1049_ip_vis_20050366
crossref_primary_10_1016_S0925_2312_00_00147_8
crossref_primary_10_1016_S0925_2312_03_00377_1
crossref_primary_10_1016_S0925_2312_03_00392_8
crossref_primary_10_4271_2014_01_9121
crossref_primary_10_1007_JHEP04_2019_037
crossref_primary_10_1016_j_isatra_2023_02_018
crossref_primary_10_1016_j_jvcir_2011_03_006
crossref_primary_10_1109_TIP_2013_2262289
crossref_primary_10_1155_2015_891692
crossref_primary_10_5391_IJFIS_2011_11_3_178
crossref_primary_10_1016_j_ejor_2005_03_072
crossref_primary_10_1109_TPAMI_2007_1085
crossref_primary_10_1109_TPAMI_2005_86
crossref_primary_10_1142_S0219477505002884
crossref_primary_10_1177_0278364915593399
crossref_primary_10_1016_j_ifacol_2020_12_006
crossref_primary_10_1109_TPAMI_2020_3048727
crossref_primary_10_1016_j_csda_2009_04_012
crossref_primary_10_1016_j_ijar_2018_02_005
crossref_primary_10_1109_TSP_2011_2180903
crossref_primary_10_3390_s17102196
crossref_primary_10_1002_dvg_20698
crossref_primary_10_1016_j_cie_2022_108383
crossref_primary_10_1152_jn_00281_2004
crossref_primary_10_1007_s00521_004_0455_7
crossref_primary_10_1109_TSP_2016_2593682
crossref_primary_10_1186_1471_2105_9_458
crossref_primary_10_1103_PhysRevD_93_012003
crossref_primary_10_1109_TCOMM_2020_3020796
crossref_primary_10_1021_ci700023y
crossref_primary_10_1088_0031_9155_60_14_5359
crossref_primary_10_1109_TMC_2011_93
crossref_primary_10_1109_TPAMI_2008_138
crossref_primary_10_1016_j_neucom_2013_12_059
crossref_primary_10_1007_JHEP10_2014_033
crossref_primary_10_1016_j_patcog_2010_02_003
crossref_primary_10_12720_jcm_9_1_81_90
crossref_primary_10_1089_106652799318274
crossref_primary_10_4236_ajcc_2021_102010
crossref_primary_10_1049_el_2011_2797
crossref_primary_10_1049_iet_cvi_2011_0017
crossref_primary_10_1111_cogs_13411
crossref_primary_10_3390_e14030456
crossref_primary_10_3390_e24091231
crossref_primary_10_1109_TSMCB_2012_2188509
crossref_primary_10_1088_1748_0221_14_06_P06032
crossref_primary_10_1137_110848281
crossref_primary_10_1016_j_patcog_2009_01_023
crossref_primary_10_1007_JHEP07_2019_142
crossref_primary_10_1016_j_cag_2021_01_008
crossref_primary_10_1088_1742_5468_aaddaa
crossref_primary_10_1109_TVT_2021_3130909
crossref_primary_10_1109_TNN_2010_2091428
crossref_primary_10_1088_1742_6596_664_8_082055
crossref_primary_10_1007_s00521_009_0281_z
crossref_primary_10_1007_JHEP06_2015_080
crossref_primary_10_1103_PhysRevA_94_012338
crossref_primary_10_1002_cpe_1762
crossref_primary_10_1109_LSP_2014_2314647
crossref_primary_10_1016_j_compbiomed_2013_07_021
crossref_primary_10_3390_e19090438
crossref_primary_10_1007_JHEP09_2018_007
crossref_primary_10_1109_JSTARS_2019_2938622
crossref_primary_10_1016_j_image_2017_12_011
crossref_primary_10_3923_itj_2010_27_33
crossref_primary_10_1109_TIP_2012_2221729
crossref_primary_10_3390_e16020968
crossref_primary_10_1109_TNSE_2019_2952454
crossref_primary_10_1109_JSTSP_2011_2138676
crossref_primary_10_1016_j_eswa_2007_09_066
crossref_primary_10_1016_j_patrec_2022_03_017
crossref_primary_10_1016_j_immuni_2019_11_014
crossref_primary_10_2514_1_61234
crossref_primary_10_1109_TKDE_2013_173
crossref_primary_10_1016_j_ecohyd_2018_07_005
crossref_primary_10_1109_TIP_2010_2081681
crossref_primary_10_1016_j_nima_2005_04_050
crossref_primary_10_1109_TAC_2011_2166713
crossref_primary_10_1109_TPAMI_2021_3109784
crossref_primary_10_1142_S0219519423400079
crossref_primary_10_1109_TSP_2009_2031283
crossref_primary_10_1016_j_automatica_2021_109564
crossref_primary_10_1109_83_841942
crossref_primary_10_1109_JSTARS_2013_2293713
crossref_primary_10_33108_visnyk_tntu2018_03_107
crossref_primary_10_1007_s10846_020_01194_0
crossref_primary_10_1007_s11042_011_0957_0
crossref_primary_10_1007_JHEP09_2014_127
crossref_primary_10_1016_j_nuclphysbps_2015_09_436
crossref_primary_10_1162_NECO_a_00012
crossref_primary_10_1073_pnas_2212660120
crossref_primary_10_1007_s10851_007_0058_x
crossref_primary_10_1109_TRO_2011_2121130
crossref_primary_10_1007_s11432_008_0079_0
crossref_primary_10_1142_S0218001407005569
crossref_primary_10_1007_s11263_018_1115_1
crossref_primary_10_1109_TCYB_2015_2501385
crossref_primary_10_1186_s12859_018_2556_9
crossref_primary_10_1007_s10439_005_9041_0
crossref_primary_10_1109_TPAMI_2007_1057
crossref_primary_10_1073_pnas_0507432102
crossref_primary_10_1109_TCOMM_2012_061412_110194
crossref_primary_10_1007_s10994_006_6540_7
crossref_primary_10_1103_PhysRevLett_100_048101
crossref_primary_10_1142_S0129626413400069
crossref_primary_10_1109_59_932293
crossref_primary_10_1016_j_jastp_2014_09_009
crossref_primary_10_1109_TNN_2009_2013708
crossref_primary_10_1016_j_procs_2010_04_007
crossref_primary_10_1007_s10489_009_0161_3
crossref_primary_10_1016_j_patcog_2008_07_004
crossref_primary_10_1088_1367_2630_ac6b30
crossref_primary_10_1155_2016_8272796
crossref_primary_10_1016_j_neucom_2009_11_022
crossref_primary_10_1109_TCOMM_2015_2494004
crossref_primary_10_1016_j_neucom_2009_11_023
crossref_primary_10_1016_S0031_3203_01_00080_2
crossref_primary_10_1109_TSP_2013_2261296
crossref_primary_10_3390_math9243224
crossref_primary_10_1007_s10827_010_0261_4
crossref_primary_10_1103_PhysRevE_103_012105
crossref_primary_10_1016_j_ijepes_2019_02_025
crossref_primary_10_1088_1748_0221_15_03_P03014
crossref_primary_10_20965_jaciii_2017_p1152
crossref_primary_10_1080_net_14_1_151_176
crossref_primary_10_1109_TIT_2003_810627
crossref_primary_10_1109_TVT_2004_841557
crossref_primary_10_1155_2012_491237
crossref_primary_10_1080_10618600_2022_2099405
crossref_primary_10_3390_e25091355
crossref_primary_10_1016_j_imavis_2006_01_028
crossref_primary_10_1109_ACCESS_2020_2964763
crossref_primary_10_1109_TAC_2022_3232706
crossref_primary_10_1109_TPAMI_2007_70775
crossref_primary_10_3390_buildings14010015
crossref_primary_10_3390_su13168900
crossref_primary_10_1007_s10107_024_02172_2
crossref_primary_10_1007_s11053_019_09510_8
crossref_primary_10_1587_transinf_E92_D_1232
crossref_primary_10_1007_JHEP05_2014_104
crossref_primary_10_1214_20_AOAS1407
crossref_primary_10_1007_s11135_014_9992_z
crossref_primary_10_1016_j_cviu_2007_07_004
crossref_primary_10_1109_TPAMI_2002_1008382
crossref_primary_10_1088_1748_0221_18_07_P07013
crossref_primary_10_1088_1742_5468_aa967e
crossref_primary_10_1073_pnas_1800521115
crossref_primary_10_1109_LRA_2020_2965893
crossref_primary_10_1016_j_patrec_2003_10_001
crossref_primary_10_1109_TPAMI_2019_2937294
crossref_primary_10_1140_epjc_s10052_011_1659_5
crossref_primary_10_1016_j_neunet_2009_08_007
crossref_primary_10_1142_S0219691316400014
crossref_primary_10_3390_su16219244
crossref_primary_10_1016_j_jtbi_2007_07_029
crossref_primary_10_1016_j_physa_2009_02_003
crossref_primary_10_1134_S1054661817030245
crossref_primary_10_1080_net_12_4_441_472
crossref_primary_10_1088_1748_0221_9_10_P10009
crossref_primary_10_1109_TFUZZ_2004_832521
crossref_primary_10_1007_s11063_006_9005_x
crossref_primary_10_1016_j_patcog_2007_05_018
crossref_primary_10_1007_JHEP02_2019_179
crossref_primary_10_1016_j_physrep_2024_09_013
crossref_primary_10_1016_j_ijar_2016_11_003
crossref_primary_10_1002_sam_10146
crossref_primary_10_1051_cocv_2005024
crossref_primary_10_1007_JHEP10_2017_076
crossref_primary_10_1109_TNNLS_2021_3138676
crossref_primary_10_1016_j_artmed_2005_01_007
crossref_primary_10_1016_j_nima_2022_166795
crossref_primary_10_1080_17457300_2017_1285789
crossref_primary_10_1109_JSTSP_2018_2846218
crossref_primary_10_1109_TKDE_2008_100
crossref_primary_10_1109_TSMCB_2005_850174
crossref_primary_10_1109_TKDE_2004_68
crossref_primary_10_1186_2042_1001_1_17
crossref_primary_10_1109_TIT_2008_928262
crossref_primary_10_1007_s13042_015_0335_8
crossref_primary_10_1109_LSP_2011_2162503
crossref_primary_10_1016_j_ijleo_2015_08_131
crossref_primary_10_1016_j_csl_2009_08_002
crossref_primary_10_1109_TIFS_2020_3002479
crossref_primary_10_3156_jfuzzy_13_4_45
crossref_primary_10_1016_j_neuroimage_2018_06_066
crossref_primary_10_3233_IFS_151971
Cites_doi 10.1109/TIT.1960.1057548
10.1109/78.98004
10.1109/TIT.1982.1056471
10.1109/34.491619
10.1109/TCOM.1980.1094577
10.1109/78.553484
10.1109/18.243432
10.1007/978-1-4471-2097-1_131
10.1109/18.340468
10.1103/PhysRevE.55.R2089
10.1080/00401706.1973.10489073
10.1016/0167-8655(90)90010-Y
10.1109/34.566806
10.1109/TPAMI.1980.4766964
10.1162/neco.1996.8.2.425
10.1109/PROC.1987.13916
10.1109/18.53739
10.1109/ASRU.1997.659125
10.1109/TIT.1984.1056920
10.1162/neco.1989.1.3.348
10.1002/j.1538-7305.1948.tb00917.x
10.1103/PhysRevE.56.3876
10.1109/TASSP.1986.1164905
10.1103/PhysRev.106.620
10.1109/5.364461
10.1109/18.144705
10.1109/TIT.1982.1056489
10.1109/ISCAS.1992.230430
10.1109/26.61363
10.1109/TIT.1987.1057376
10.1109/ICC.1988.13817
10.1109/78.650107
10.1162/neco.1991.3.2.268
10.1109/78.124940
10.1063/1.1699114
10.1002/ecja.4400670406
10.1002/bs.3830120210
10.1109/ICASSP.1994.389482
10.1109/TIT.1980.1056144
10.1109/TASSP.1980.1163445
10.1109/DCC.1993.253149
10.1109/TAC.1974.1100705
10.1109/IJCNN.1991.155153
10.1109/18.32124
10.1109/21.229447
10.1162/neco.1993.5.1.89
10.1007/978-1-4757-2024-2
10.1109/TIT.1982.1056456
10.1109/34.748824
10.1109/34.236251
10.1109/NNSP.1997.622407
10.1162/neco.1994.6.2.181
10.1016/0095-0696(78)90006-2
10.1080/01969727308546046
10.1109/72.80234
10.1162/neco.1990.2.1.1
10.1109/TCOMM.1994.577056
10.1109/CDC.1985.268599
10.1109/29.17498
10.1109/34.88569
10.1109/TIT.1981.1056366
10.1109/TPAMI.1984.4767596
10.7551/mitpress/5236.001.0001
10.1142/S0129065795000251
10.1162/neco.1991.3.1.79
10.1109/34.134040
10.1049/ip-i-2.1989.0061
10.1109/TCOM.1969.1090091
10.1103/PhysRevLett.65.945
10.1214/aos/1176350051
10.1049/ip-vis:19941324
10.1126/science.220.4598.671
10.1109/72.286906
10.1109/34.310694
10.1109/72.238311
10.1109/TIT.1972.1054855
10.1038/326689a0
10.1109/ICNN.1988.23829
10.1016/S0893-6080(05)80038-3
10.1109/ICASSP.1996.544855
10.1109/72.105426
10.1214/aoms/1177697196
10.1162/neco.1989.1.2.281
10.1088/0954-898X/1/1/007
10.1109/18.61130
10.1109/TIT.1972.1054753
ContentType Journal Article
DBID RIA
RIE
AAYXX
CITATION
DOI 10.1109/5.726788
DatabaseName IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Xplore
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Physics
EndPage 2239
ExternalDocumentID 10_1109_5_726788
726788
GroupedDBID -DZ
-~X
.DC
0R~
123
1OL
29P
3EH
4.4
6IK
85S
9M8
AAJGR
AAWTH
ABAZT
ABFSI
ABJNI
ABQJQ
ABVLG
ACBEA
ACGFS
AENEX
AETEA
AETIX
AFOGA
AGNAY
AGQYO
AGSQL
AHBIQ
AIBXA
ALLEH
ALMA_UNASSIGNED_HOLDINGS
AZLTO
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
FA8
HZ~
H~9
IAAWW
IBMZZ
ICLAB
IDIHD
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MVM
O9-
OCL
RIA
RIE
RIU
RNS
TAE
TN5
TWZ
UDY
UHB
UKR
UQL
VOH
WHG
XJT
XOL
YNT
ZCA
ZXP
ZY4
~02
AAYXX
CITATION
ID FETCH-LOGICAL-c310t-ba7040e10b31a665f67dc0ea24be2a87ecf80efd08b1defc0f7b0d1c8ec06c053
IEDL.DBID RIE
ISSN 0018-9219
IngestDate Wed Oct 01 04:27:59 EDT 2025
Thu Apr 24 23:13:04 EDT 2025
Wed Aug 27 02:43:11 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 11
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c310t-ba7040e10b31a665f67dc0ea24be2a87ecf80efd08b1defc0f7b0d1c8ec06c053
PageCount 30
ParticipantIDs crossref_primary_10_1109_5_726788
ieee_primary_726788
crossref_citationtrail_10_1109_5_726788
ProviderPackageCode CITATION
AAYXX
PublicationCentury 1900
PublicationDate 1998-11-01
PublicationDateYYYYMMDD 1998-11-01
PublicationDate_xml – month: 11
  year: 1998
  text: 1998-11-01
  day: 01
PublicationDecade 1990
PublicationTitle Proceedings of the IEEE
PublicationTitleAbbrev JPROC
PublicationYear 1998
Publisher IEEE
Publisher_xml – name: IEEE
References ref57
ref56
ref59
ref58
ref53
ref52
ref55
rao (ref77) 1998
szu (ref100) 1987; 75
ref51
ref50
fix (ref31) 1978
berger (ref7) 1971
blahut (ref12) 1987
rose (ref86) 1991
ref47
ref42
ref41
ref43
breiman (ref13) 1980
ripley (ref83) 1994; 56
ref49
ref8
ref9
ref4
ref3
ref6
ref5
ref101
duda (ref23) 1974
ref35
ref34
ref37
ref30
kirkpatrick (ref54) 1983; 220
ref33
dempster (ref21) 1977; 39
ref39
ref38
gersho (ref36) 1991
hu (ref48) 1995
ref24
ref26
ref25
ref20
ref22
ueda (ref103) 1994
ref28
ref27
luttrell (ref61) 1989; 136
ref29
gray (ref40) 1990
miller (ref69) 1995
haykin (ref45) 1998
ref15
macqueen (ref63) 1967
ref14
ref97
ref99
ref11
ref98
ref10
ref17
ref16
ref19
ref18
gallager (ref32) 1968
ref92
ref95
ref91
royden (ref93) 1988
ref90
ref89
ref85
ref88
ref87
ref82
ref81
ref84
ref80
hinton (ref46) 1995; 8
ref79
ref108
ref78
ref109
ref106
ref107
ref75
ref74
ref105
ref76
ref2
ref1
mclachlan (ref67) 1988
titterington (ref102) 1985
ref71
waterhouse (ref104) 1994; 7
ref70
ref73
ref72
ref110
ref68
hartigan (ref44) 1975
ref64
ref66
ref65
shannon (ref96) 1959
ref60
ref62
rumelhart (ref94) 1986
References_xml – ident: ref65
  doi: 10.1109/TIT.1960.1057548
– ident: ref84
  doi: 10.1109/78.98004
– ident: ref41
  doi: 10.1109/TIT.1982.1056471
– ident: ref37
  doi: 10.1109/34.491619
– volume: 39
  start-page: 1
  year: 1977
  ident: ref21
  article-title: maximum-likelihood from incomplete data via the em algorithm
  publication-title: J Roy Stat Soc
– ident: ref59
  doi: 10.1109/TCOM.1980.1094577
– ident: ref70
  doi: 10.1109/78.553484
– year: 1975
  ident: ref44
  publication-title: Clustering Algorithms
– ident: ref14
  doi: 10.1109/18.243432
– ident: ref110
  doi: 10.1007/978-1-4471-2097-1_131
– ident: ref87
  doi: 10.1109/18.340468
– ident: ref55
  doi: 10.1103/PhysRevE.55.R2089
– ident: ref66
  doi: 10.1080/00401706.1973.10489073
– ident: ref88
  doi: 10.1016/0167-8655(90)90010-Y
– year: 1988
  ident: ref93
  publication-title: Real Analysis
– year: 1991
  ident: ref86
  publication-title: Deterministic annealing clustering and optimization
– ident: ref47
  doi: 10.1109/34.566806
– ident: ref9
  doi: 10.1109/TPAMI.1980.4766964
– ident: ref73
  doi: 10.1162/neco.1996.8.2.425
– volume: 75
  start-page: 1538
  year: 1987
  ident: ref100
  article-title: nonconvex optimization by fast simulated annealing
  publication-title: Proceedings of the IEEE
  doi: 10.1109/PROC.1987.13916
– ident: ref28
  doi: 10.1109/18.53739
– year: 1998
  ident: ref45
  publication-title: Neural Networks A Comprehensive Foundation
– ident: ref80
  doi: 10.1109/ASRU.1997.659125
– ident: ref29
  doi: 10.1109/TIT.1984.1056920
– ident: ref26
  doi: 10.1162/neco.1989.1.3.348
– ident: ref95
  doi: 10.1002/j.1538-7305.1948.tb00917.x
– ident: ref38
  doi: 10.1103/PhysRevE.56.3876
– ident: ref16
  doi: 10.1109/TASSP.1986.1164905
– ident: ref52
  doi: 10.1103/PhysRev.106.620
– ident: ref22
  doi: 10.1109/5.364461
– ident: ref90
  doi: 10.1109/18.144705
– ident: ref60
  doi: 10.1109/TIT.1982.1056489
– ident: ref92
  doi: 10.1109/ISCAS.1992.230430
– ident: ref35
  doi: 10.1109/26.61363
– ident: ref3
  doi: 10.1109/TIT.1987.1057376
– ident: ref109
  doi: 10.1109/ICC.1988.13817
– ident: ref82
  doi: 10.1109/78.650107
– ident: ref99
  doi: 10.1162/neco.1991.3.2.268
– year: 1991
  ident: ref36
  publication-title: Vector Quantization and Signal Compression
– ident: ref107
  doi: 10.1109/78.124940
– year: 1995
  ident: ref69
  publication-title: An information-theoretic framework for optimization with applications in source coding and pattern recognition
– ident: ref68
  doi: 10.1063/1.1699114
– ident: ref57
  doi: 10.1002/ecja.4400670406
– ident: ref4
  doi: 10.1002/bs.3830120210
– year: 1968
  ident: ref32
  publication-title: Information Theory and Reliable Communication
– ident: ref74
  doi: 10.1109/ICASSP.1994.389482
– ident: ref97
  doi: 10.1109/TIT.1980.1056144
– ident: ref15
  doi: 10.1109/TASSP.1980.1163445
– ident: ref71
  doi: 10.1109/DCC.1993.253149
– ident: ref1
  doi: 10.1109/TAC.1974.1100705
– year: 1971
  ident: ref7
  publication-title: Rate Distortion Theory
– ident: ref17
  doi: 10.1109/IJCNN.1991.155153
– year: 1998
  ident: ref77
  publication-title: Design of pattern recognition systems using deterministic annealing Applications in speech recognition regression and data compression
– ident: ref20
  doi: 10.1109/18.32124
– ident: ref50
  doi: 10.1109/21.229447
– year: 1985
  ident: ref102
  publication-title: Analysis of Finite Mixture Distributions
– ident: ref106
  doi: 10.1162/neco.1993.5.1.89
– ident: ref39
  doi: 10.1007/978-1-4757-2024-2
– ident: ref8
  doi: 10.1109/TIT.1982.1056456
– ident: ref78
  doi: 10.1109/34.748824
– ident: ref91
  doi: 10.1109/34.236251
– ident: ref81
  doi: 10.1109/NNSP.1997.622407
– ident: ref53
  doi: 10.1162/neco.1994.6.2.181
– ident: ref43
  doi: 10.1016/0095-0696(78)90006-2
– year: 1980
  ident: ref13
  publication-title: Classification and Regression Trees
– volume: 56
  start-page: 409
  year: 1994
  ident: ref83
  article-title: neural networks and related methods for classification
  publication-title: J Roy Stat Soc
– ident: ref25
  doi: 10.1080/01969727308546046
– ident: ref62
  doi: 10.1109/72.80234
– ident: ref108
  doi: 10.1162/neco.1990.2.1.1
– ident: ref72
  doi: 10.1109/TCOMM.1994.577056
– year: 1974
  ident: ref23
  publication-title: Pattern Classification and Scene Analysis
– year: 1987
  ident: ref12
  publication-title: Principles and Practice of Information Theory
– start-page: 704
  year: 1978
  ident: ref31
  article-title: rate distortion functions for squared error distortion measures
  publication-title: Proc 16th Annu Allerton Conf Communications Control and Computers
– year: 1988
  ident: ref67
  publication-title: Mixture Models Inference and Application to Clustering
– ident: ref42
  doi: 10.1109/CDC.1985.268599
– ident: ref19
  doi: 10.1109/29.17498
– ident: ref18
  doi: 10.1109/34.88569
– ident: ref24
  doi: 10.1109/TIT.1981.1056366
– volume: 8
  start-page: 507
  year: 1995
  ident: ref46
  article-title: using pairs of data points to define splits for decision trees
  publication-title: Neural Inform Processing Syst
– start-page: 142
  year: 1959
  ident: ref96
  article-title: coding theorems for a discrete source with a fidelity criterion
  publication-title: IRE Nat Conv Rec
– ident: ref34
  doi: 10.1109/TPAMI.1984.4767596
– year: 1986
  ident: ref94
  publication-title: Parallel Distributed Processing
  doi: 10.7551/mitpress/5236.001.0001
– ident: ref105
  doi: 10.1142/S0129065795000251
– ident: ref51
  doi: 10.1162/neco.1991.3.1.79
– ident: ref33
  doi: 10.1109/34.134040
– volume: 136
  start-page: 405
  year: 1989
  ident: ref61
  article-title: hierarchical vector quantisation (image compression)
  publication-title: Communications Speech and Vision IEE Proceedings I
  doi: 10.1049/ip-i-2.1989.0061
– ident: ref58
  doi: 10.1109/TCOM.1969.1090091
– ident: ref89
  doi: 10.1103/PhysRevLett.65.945
– ident: ref85
  doi: 10.1214/aos/1176350051
– volume: 7
  start-page: 835
  year: 1994
  ident: ref104
  article-title: non-linear prediction of acoustic vectors using hierarchical mixtures of experts
  publication-title: Proc Neural Inform Processing Syst
– start-page: 459
  year: 1995
  ident: ref48
  article-title: customized ecg beat classifier using mixture of experts
  publication-title: Proc IEEE Workshop on Neural Networks for Signal Processing
– ident: ref101
  doi: 10.1049/ip-vis:19941324
– year: 1990
  ident: ref40
  publication-title: Source Coding Theory
– start-page: 281
  year: 1967
  ident: ref63
  article-title: some methods for classification and analysis of multivariate observations
  publication-title: Proc 5th Berkeley Symp Math Statistics and Probability
– volume: 220
  start-page: 671
  year: 1983
  ident: ref54
  article-title: optimization by simulated annealing
  publication-title: Science
  doi: 10.1126/science.220.4598.671
– ident: ref49
  doi: 10.1109/72.286906
– ident: ref6
  doi: 10.1109/34.310694
– ident: ref64
  doi: 10.1109/72.238311
– ident: ref11
  doi: 10.1109/TIT.1972.1054855
– ident: ref27
  doi: 10.1038/326689a0
– ident: ref56
  doi: 10.1109/ICNN.1988.23829
– ident: ref76
  doi: 10.1016/S0893-6080(05)80038-3
– start-page: 545
  year: 1994
  ident: ref103
  article-title: deterministic annealing variant of the em algorithm
  publication-title: Proc Neural Information Processing Systems
– ident: ref79
  doi: 10.1109/ICASSP.1996.544855
– ident: ref10
  doi: 10.1109/72.105426
– ident: ref5
  doi: 10.1214/aoms/1177697196
– ident: ref75
  doi: 10.1162/neco.1989.1.2.281
– ident: ref98
  doi: 10.1088/0954-898X/1/1/007
– ident: ref30
  doi: 10.1109/18.61130
– ident: ref2
  doi: 10.1109/TIT.1972.1054753
SSID ssj0003563
Score 2.2019143
Snippet The deterministic annealing approach to clustering and its extensions has demonstrated substantial performance improvement over standard supervised and...
SourceID crossref
ieee
SourceType Enrichment Source
Index Database
Publisher
StartPage 2210
SubjectTerms Annealing
Constraint optimization
Costs
Decision trees
Multilayer perceptrons
Pattern recognition
Physics
Rate-distortion
Temperature
Unsupervised learning
Title Deterministic annealing for clustering, compression, classification, regression, and related optimization problems
URI https://ieeexplore.ieee.org/document/726788
Volume 86
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Xplore
  issn: 0018-9219
  databaseCode: RIE
  dateStart: 19630101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://ieeexplore.ieee.org/
  omitProxy: false
  ssIdentifier: ssj0003563
  providerName: IEEE
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LS8NAEF5sQdCDj6pYX6wgeGnazXtzFLUUQU8Wegv7mHiwptImF3-9s5s1VOnBWza7gZDdmZ3Jft83hNyYs5nIQHVCXQReFGWpJ9Is8BSmzFqFGQQWVfn8kkym0dMsnjmdbcuFAQALPoOhubRn-XqhavOrbJQG6Fp5h3RSnjRUrdbphrErmuaj_aIVOp1Zn2WjeNg892vnWSulYneS8X5D0V5ZAUIDIHkf1pUcqq8_8oz_fMkDsuciSnrXLIFDsgVlj-yu6Qz2yLbFearVEVk-OPiL1WemAr2sMIR0irErVfPayCZgc0AN1LyByJbYMCG2wRTZaRzQJby1faLU1BJiQNMF-p8PR-ykrlTN6phMx4-v9xPPlV3wFMZ6lSdFipYNPpOhL5IkLpJUKwYiiCQEgqegCs6g0IxLX0OhWJFKpn3FQbFEoVGfkG65KOGUUCkyEFxmmHNi4hYGXEQC8x3ArK4QgfT75PZnSnLlNMlNaYx5bnMTluVx3nzPPrluR342OhwbxvTMdLT9zd2zjXfPyY5lF1pW4QXpVssaLjG8qOSVXVjfXKfQ2g
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3JTsMwELWgCAEHlgKirEZC4kJSJ3G2IwKqsrQnkHqLvEw4UFLU5cLXM3ZMBagHbnHsSFHsGc_E770h5MKczXAD1Yl0GXqc56kn0jz0FKbMWkU5hBZV2esn3Rf-MIgHTmfbcmEAwILPwDeX9ixfj9TM_CprpyG61myZrMSc87gma83dbhS7smkBWjDaoVOaDVjejv36yV97z49iKnYv6WzVJO2JlSA0EJI3fzaVvvr8I9D4z9fcJpsupqTX9SLYIUtQNcnGD6XBJlm1SE812SXjWweAsQrNVKCfFYaSTjF6pWo4M8IJ2LyiBmxeg2QrbJgg26CK7ERe0TG8zvtEpamlxICmI_RA747aSV2xmskeeencPd90PVd4wVMY7U09KVK0bQiYjAKRJHGZpFoxECGXEIosBVVmDErNMhloKBUrU8l0oDJQLFFo1vukUY0qOCBUihxEJnPMOjF1i8JMcIEZD2BeV4pQBi1y-T0lhXKq5KY4xrCw2QnLi7iov2eLnM9HftRKHAvGNM10zPvru4cL756Rte5z76l4uu8_HpF1yzW0HMNj0piOZ3CCwcZUntpF9gVutNQn
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=Deterministic+annealing+for+clustering%2C+compression%2C+classification%2C+regression%2C+and+related+optimization+problems&rft.jtitle=Proceedings+of+the+IEEE&rft.au=Rose%2C+K.&rft.date=1998-11-01&rft.issn=0018-9219&rft.volume=86&rft.issue=11&rft.spage=2210&rft.epage=2239&rft_id=info:doi/10.1109%2F5.726788&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_5_726788
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9219&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9219&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9219&client=summon