A review of unsupervised feature learning and deep learning for time-series modeling
This paper gives a review of the recent developments in deep learning and unsupervised feature learning for time-series problems. While these techniques have shown promise for modeling static data, such as computer vision, applying them to time-series data is gaining increasing attention. This paper...
Saved in:
| Published in | Pattern recognition letters Vol. 42; no. 1; pp. 11 - 24 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
01.06.2014
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 0167-8655 1872-7344 1872-7344 |
| DOI | 10.1016/j.patrec.2014.01.008 |
Cover
| Abstract | This paper gives a review of the recent developments in deep learning and unsupervised feature learning for time-series problems. While these techniques have shown promise for modeling static data, such as computer vision, applying them to time-series data is gaining increasing attention. This paper overviews the particular challenges present in time-series data and provides a review of the works that have either applied time-series data to unsupervised feature learning algorithms or alternatively have contributed to modifications of feature learning algorithms to take into account the challenges present in time-series data. |
|---|---|
| AbstractList | This paper gives a review of the recent developments in deep learning and unsupervised feature learning for time-series problems. While these techniques have shown promise for modeling static data, such as computer vision, applying them to time-series data is gaining increasing attention. This paper overviews the particular challenges present in time-series data and provides a review of the works that have either applied time-series data to unsupervised feature learning algorithms or alternatively have contributed to modifications of feature learning algorithms to take into account the challenges present in time-series data. |
| Author | Loutfi, Amy Längkvist, Martin Karlsson, Lars |
| Author_xml | – sequence: 1 givenname: Martin surname: Längkvist fullname: Längkvist, Martin email: martin.langkvist@oru.se – sequence: 2 givenname: Lars surname: Karlsson fullname: Karlsson, Lars email: lars.karlsson@oru.se – sequence: 3 givenname: Amy surname: Loutfi fullname: Loutfi, Amy email: amy.loutfi@oru.se |
| BackLink | https://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-34597$$DView record from Swedish Publication Index |
| BookMark | eNqNkctKAzEUhoNUsFbfwEUewBmTuWZcCKVeoeCmug2ZzElJmSZDMtPStzdlRMGFugiBc_7vJHznHE2MNYDQFSUxJbS42cSd6B3IOCE0iwmNCWEnaEpZmURlmmUTNA2xMmJFnp-hc-83hJAirdgUrebYwU7DHluFB-OHDtxOe2iwAtEPDnALwhlt1liYBjcA3XdFWYd7vYXIg9Pg8dY20IbGBTpVovVw-XnP0Nvjw2rxHC1fn14W82UkU1b1EaiyrhgomYIkOaGJyGkKrCA0VERdAyM1rau6rBjLaaESxSCXMqtoFSAl0hnKx7mD6cRhL9qWd05vhTtwSvhRDd_wUQ0_quGE8qAmcNcj5_fQDfUXZIXm9_p9zq1bhzPwNMurMsRvx7h01nsHikvdi15b0zuh27_eyn7A__zi3YhB8Bf247iXGoyERodozxurfx_wAVHxp7o |
| CitedBy_id | crossref_primary_10_1016_j_knosys_2022_108459 crossref_primary_10_1080_01932691_2023_2178453 crossref_primary_10_1016_j_asoc_2017_06_046 crossref_primary_10_1109_ACCESS_2024_3413948 crossref_primary_10_1155_2019_9240317 crossref_primary_10_1109_TNNLS_2022_3149091 crossref_primary_10_1016_j_asoc_2022_109726 crossref_primary_10_1109_JBHI_2020_2977937 crossref_primary_10_1166_jmihi_2021_3471 crossref_primary_10_1038_s41598_024_56674_2 crossref_primary_10_1080_14697688_2019_1634277 crossref_primary_10_1002_gdj3_281 crossref_primary_10_1016_j_eswa_2016_02_006 crossref_primary_10_1088_2057_1976_ad7bc0 crossref_primary_10_32604_iasc_2024_055133 crossref_primary_10_1002_rse2_141 crossref_primary_10_1016_j_eswa_2023_120619 crossref_primary_10_1109_TKDE_2019_2954510 crossref_primary_10_1016_j_neucom_2018_05_090 crossref_primary_10_1109_ACCESS_2024_3384066 crossref_primary_10_1145_3533382 crossref_primary_10_1007_s11269_016_1474_8 crossref_primary_10_1186_s13635_019_0090_6 crossref_primary_10_2339_politeknik_620613 crossref_primary_10_1016_j_eswa_2016_10_010 crossref_primary_10_1016_j_knosys_2018_06_026 crossref_primary_10_1016_j_enconman_2018_04_082 crossref_primary_10_1002_ente_202401696 crossref_primary_10_3390_en11082008 crossref_primary_10_1007_s11377_020_00494_z crossref_primary_10_1016_j_eswa_2017_04_028 crossref_primary_10_3390_rs15194665 crossref_primary_10_3390_w15213779 crossref_primary_10_1016_j_future_2019_05_074 crossref_primary_10_31466_kfbd_1434595 crossref_primary_10_1016_j_apenergy_2017_03_064 crossref_primary_10_1109_JPROC_2023_3309299 crossref_primary_10_1109_TCYB_2016_2533545 crossref_primary_10_2118_221461_PA crossref_primary_10_1016_j_eswa_2017_04_030 crossref_primary_10_1109_TITS_2018_2797943 crossref_primary_10_1142_S1469026821500103 crossref_primary_10_1007_s12559_023_10122_x crossref_primary_10_3390_s17071564 crossref_primary_10_1016_j_energy_2022_125826 crossref_primary_10_3390_rs12244172 crossref_primary_10_1016_j_agsy_2021_103208 crossref_primary_10_1016_j_trf_2017_11_021 crossref_primary_10_1007_s10142_023_01064_6 crossref_primary_10_1364_OE_27_037150 crossref_primary_10_1007_s00500_023_08571_5 crossref_primary_10_3389_fenrg_2020_00179 crossref_primary_10_1109_JBHI_2020_2984128 crossref_primary_10_1002_eng2_12589 crossref_primary_10_3390_aerospace6110117 crossref_primary_10_3390_s24092833 crossref_primary_10_1155_2017_7259762 crossref_primary_10_1155_2019_2985014 crossref_primary_10_1527_tjsai_35_5_B_K33 crossref_primary_10_3390_buildings13030627 crossref_primary_10_1016_j_knosys_2019_105022 crossref_primary_10_1038_s41598_020_61173_1 crossref_primary_10_1016_j_neucom_2021_04_051 crossref_primary_10_1109_TVT_2019_2949954 crossref_primary_10_2166_hydro_2023_170 crossref_primary_10_1007_s40436_024_00526_9 crossref_primary_10_1109_ACCESS_2021_3079447 crossref_primary_10_1080_08982112_2022_2087041 crossref_primary_10_1109_ACCESS_2019_2941799 crossref_primary_10_1364_AO_58_000164 crossref_primary_10_1016_j_artmed_2022_102486 crossref_primary_10_1109_TMM_2019_2895505 crossref_primary_10_3390_w14050763 crossref_primary_10_1007_s11336_022_09858_6 crossref_primary_10_1109_ACCESS_2021_3076281 crossref_primary_10_3390_s23010062 crossref_primary_10_1109_TIM_2016_2573078 crossref_primary_10_3390_s19092201 crossref_primary_10_3390_electronics11152280 crossref_primary_10_1016_j_cma_2024_117399 crossref_primary_10_1088_1757_899X_1238_1_012065 crossref_primary_10_1016_j_procir_2021_11_261 crossref_primary_10_3390_s21020603 crossref_primary_10_1016_j_apacoust_2019_107141 crossref_primary_10_3390_f16030449 crossref_primary_10_1016_j_eswa_2020_113271 crossref_primary_10_3390_ijms20112656 crossref_primary_10_1016_j_heliyon_2022_e08803 crossref_primary_10_1016_j_bspc_2017_06_012 crossref_primary_10_1016_j_ins_2014_05_029 crossref_primary_10_1109_ACCESS_2020_3029202 crossref_primary_10_3233_AF_180235 crossref_primary_10_1016_j_isatra_2020_07_039 crossref_primary_10_1016_j_optlastec_2023_109807 crossref_primary_10_1002_cpe_4403 crossref_primary_10_3389_fbioe_2024_1351485 crossref_primary_10_1109_TBDATA_2019_2918807 crossref_primary_10_1007_s12145_020_00462_9 crossref_primary_10_1061__ASCE_HE_1943_5584_0001694 crossref_primary_10_1016_j_cj_2019_06_005 crossref_primary_10_1088_1741_2552_abd461 crossref_primary_10_1016_j_patrec_2016_12_018 crossref_primary_10_1007_s12652_018_0867_3 crossref_primary_10_3233_JIFS_221188 crossref_primary_10_3389_frobt_2016_00076 crossref_primary_10_1016_j_eswa_2022_119152 crossref_primary_10_1371_journal_pone_0175025 crossref_primary_10_1016_j_eswa_2020_113562 crossref_primary_10_1016_j_scitotenv_2020_140338 crossref_primary_10_1371_journal_pone_0212137 crossref_primary_10_5194_essd_17_1173_2025 crossref_primary_10_1016_j_neucom_2021_10_010 crossref_primary_10_1109_ACCESS_2018_2877097 crossref_primary_10_3390_mi13030363 crossref_primary_10_1038_s41598_019_48874_y crossref_primary_10_1007_s10479_024_06056_8 crossref_primary_10_1016_j_yebeh_2018_11_011 crossref_primary_10_1007_s11063_020_10248_1 crossref_primary_10_1016_j_jvcir_2018_06_030 crossref_primary_10_1080_15376494_2023_2253548 crossref_primary_10_1061_JBENF2_BEENG_6012 crossref_primary_10_1016_j_enconman_2018_03_098 crossref_primary_10_1016_j_eswa_2020_113337 crossref_primary_10_1049_cmu2_12783 crossref_primary_10_1080_08839514_2020_1713454 crossref_primary_10_1515_comp_2022_0236 crossref_primary_10_3390_s20010168 crossref_primary_10_1016_j_neucom_2020_07_108 crossref_primary_10_1016_j_bspc_2024_105971 crossref_primary_10_1007_s11277_017_5086_2 crossref_primary_10_1016_j_ymssp_2020_107072 crossref_primary_10_1109_ACCESS_2023_3235619 crossref_primary_10_1109_COMST_2022_3232576 crossref_primary_10_1016_j_patrec_2017_06_008 crossref_primary_10_1007_s00607_024_01370_2 crossref_primary_10_1109_JBHI_2017_2727218 crossref_primary_10_1016_j_jbi_2020_103565 crossref_primary_10_1016_j_future_2017_08_031 crossref_primary_10_3390_s20030903 crossref_primary_10_3390_s19112429 crossref_primary_10_3233_KES220010 crossref_primary_10_1007_s42979_022_01161_6 crossref_primary_10_3390_electronics10222851 crossref_primary_10_1109_TIM_2020_3017246 crossref_primary_10_24012_dumf_1079230 crossref_primary_10_1007_s13369_024_09818_5 crossref_primary_10_1016_j_eswa_2020_113463 crossref_primary_10_1175_JTECH_D_18_0141_1 crossref_primary_10_1016_j_cnsns_2019_105139 crossref_primary_10_1109_ACCESS_2020_3047186 crossref_primary_10_1109_ACCESS_2020_2995198 crossref_primary_10_1002_eng2_12541 crossref_primary_10_3390_electronics12051188 crossref_primary_10_1051_shsconf_202419703002 crossref_primary_10_3390_ijerph191912528 crossref_primary_10_2139_ssrn_3165408 crossref_primary_10_1109_JPROC_2015_2491979 crossref_primary_10_1186_s12911_024_02474_7 crossref_primary_10_1061_JWRMD5_WRENG_5444 crossref_primary_10_1016_j_bir_2024_01_011 crossref_primary_10_1016_j_cma_2019_05_052 crossref_primary_10_3233_ICA_210650 crossref_primary_10_1063_5_0024890 crossref_primary_10_1016_j_inffus_2018_09_001 crossref_primary_10_1007_s10489_022_03761_4 crossref_primary_10_1016_j_ribaf_2020_101291 crossref_primary_10_1016_j_jksuci_2019_02_001 crossref_primary_10_1016_j_jwpe_2024_105831 crossref_primary_10_1016_j_knosys_2017_03_027 crossref_primary_10_3390_s20144026 crossref_primary_10_1117_1_JRS_11_042609 crossref_primary_10_1002_nme_6918 crossref_primary_10_1007_s10618_019_00619_1 crossref_primary_10_1088_1742_6596_1496_1_012002 crossref_primary_10_1109_ACCESS_2021_3050836 crossref_primary_10_3390_s23115013 crossref_primary_10_1016_j_engappai_2023_106440 crossref_primary_10_3390_su10103498 crossref_primary_10_1007_s12206_018_1205_6 crossref_primary_10_1142_S1793545816300111 crossref_primary_10_1002_adma_201905522 crossref_primary_10_1016_j_neunet_2022_12_004 crossref_primary_10_1109_JBHI_2018_2879381 crossref_primary_10_1016_j_compind_2021_103421 crossref_primary_10_36558_22372903_2019V9N1_P3 crossref_primary_10_1016_j_knosys_2020_106551 crossref_primary_10_1016_j_conb_2018_12_010 crossref_primary_10_1097_PCC_0000000000001666 crossref_primary_10_3390_s21227620 crossref_primary_10_1007_s12046_023_02086_3 crossref_primary_10_1016_j_arcontrol_2019_07_003 crossref_primary_10_1109_TNNLS_2020_3017200 crossref_primary_10_1088_1361_6579_aad5bd crossref_primary_10_1142_S0218001418500118 crossref_primary_10_1016_j_arr_2024_102651 crossref_primary_10_2139_ssrn_3394704 crossref_primary_10_1016_j_jksuci_2023_101820 crossref_primary_10_1016_j_knosys_2023_110660 crossref_primary_10_3390_e24020141 crossref_primary_10_1007_s00521_021_06212_2 crossref_primary_10_1007_s11036_020_01647_8 crossref_primary_10_1109_TKDE_2018_2863705 crossref_primary_10_1016_j_neucom_2022_03_014 crossref_primary_10_3390_app11199243 crossref_primary_10_1016_j_ndteint_2022_102756 crossref_primary_10_1109_OJITS_2022_3177007 crossref_primary_10_3390_s23229099 crossref_primary_10_3390_sym13101942 crossref_primary_10_1016_j_knosys_2014_12_003 crossref_primary_10_1007_s40747_021_00637_x crossref_primary_10_1088_1757_899X_981_2_022021 crossref_primary_10_7717_peerj_cs_514 crossref_primary_10_1109_ACCESS_2019_2959022 crossref_primary_10_7717_peerj_cs_638 crossref_primary_10_1007_s00521_017_3324_x crossref_primary_10_1021_acs_chemrestox_0c00316 crossref_primary_10_1088_1742_6596_1028_1_012212 crossref_primary_10_3389_fvets_2019_00153 crossref_primary_10_1109_JIOT_2024_3383512 crossref_primary_10_1103_PhysRevE_100_032410 crossref_primary_10_1007_s10489_021_02416_0 crossref_primary_10_1109_TIM_2021_3068180 crossref_primary_10_1016_j_compag_2025_110147 crossref_primary_10_1109_ACCESS_2019_2916793 crossref_primary_10_3390_diagnostics13243673 crossref_primary_10_1109_TNSRE_2022_3216528 crossref_primary_10_1080_0951192X_2022_2025623 crossref_primary_10_1016_j_chemolab_2020_103932 crossref_primary_10_1016_j_neucom_2021_02_046 crossref_primary_10_3390_s21165386 crossref_primary_10_1016_j_apenergy_2017_12_005 crossref_primary_10_1142_S1469026816500218 crossref_primary_10_1016_j_asoc_2024_111749 crossref_primary_10_1007_s00521_022_07328_9 crossref_primary_10_1088_2634_4386_ac734a crossref_primary_10_2139_ssrn_4102488 crossref_primary_10_1109_ACCESS_2020_3025808 crossref_primary_10_1016_j_ast_2024_109760 crossref_primary_10_1007_s10489_019_01552_y crossref_primary_10_1142_S0129183120501387 crossref_primary_10_3390_app14135658 crossref_primary_10_1097_CCM_0000000000003854 crossref_primary_10_1007_s10618_024_01018_x crossref_primary_10_3390_s19184009 crossref_primary_10_1016_j_knosys_2020_105596 crossref_primary_10_3390_en13205504 crossref_primary_10_1007_s00521_020_05262_2 crossref_primary_10_1109_TIM_2020_3026497 crossref_primary_10_1177_0954406219834048 crossref_primary_10_1007_s11852_024_01038_1 crossref_primary_10_1016_j_neucom_2016_03_057 crossref_primary_10_1007_s11071_023_08251_x crossref_primary_10_1016_j_jbi_2020_103627 crossref_primary_10_7717_peerj_8207 crossref_primary_10_1016_j_ijhydene_2024_05_338 crossref_primary_10_1007_s10489_023_05079_1 crossref_primary_10_3390_s23020826 crossref_primary_10_1093_mnras_stab3043 crossref_primary_10_1177_00202940221099064 crossref_primary_10_1155_2022_2897672 crossref_primary_10_1007_s42979_023_02159_4 crossref_primary_10_1016_j_ecoinf_2014_08_009 crossref_primary_10_1016_j_procs_2023_01_116 crossref_primary_10_1109_ACCESS_2021_3099111 crossref_primary_10_1109_TIE_2017_2767540 crossref_primary_10_1109_RBME_2017_2757953 crossref_primary_10_26599_BDMA_2023_9020028 crossref_primary_10_54097_jceim_v10i1_5763 crossref_primary_10_1016_j_geoen_2023_212528 crossref_primary_10_1159_000501735 crossref_primary_10_1109_LSENS_2018_2884735 crossref_primary_10_1177_09544054241229495 crossref_primary_10_1016_j_measurement_2019_106857 crossref_primary_10_1109_ACCESS_2022_3221436 crossref_primary_10_1109_TIA_2020_2976722 crossref_primary_10_1016_j_talanta_2021_122195 crossref_primary_10_1016_j_ipm_2023_103579 crossref_primary_10_1007_s11709_023_0942_5 crossref_primary_10_1109_TGRS_2017_2692281 crossref_primary_10_1155_2020_6518147 crossref_primary_10_1016_j_neucom_2018_09_082 crossref_primary_10_1109_ACCESS_2024_3516215 crossref_primary_10_1016_j_knosys_2017_09_023 crossref_primary_10_1007_s10489_023_05155_6 crossref_primary_10_1080_10106049_2021_1926555 crossref_primary_10_1016_j_neucom_2023_126435 crossref_primary_10_3103_S0747923918010073 crossref_primary_10_1051_wujns_2022276521 crossref_primary_10_1016_j_engappai_2022_105591 crossref_primary_10_3390_rs10030452 crossref_primary_10_1016_j_bspc_2016_11_013 crossref_primary_10_1016_j_cmpb_2018_04_005 crossref_primary_10_1049_iet_spr_2020_0154 crossref_primary_10_1177_1475921720942836 crossref_primary_10_1007_s11071_015_2571_6 crossref_primary_10_3390_s22093468 crossref_primary_10_1007_s42488_019_00004_z crossref_primary_10_1016_j_cie_2023_109701 crossref_primary_10_1038_s42003_021_01699_w crossref_primary_10_26599_TST_2023_9010056 crossref_primary_10_1007_s00103_019_03080_z crossref_primary_10_1080_1051712X_2024_2397542 crossref_primary_10_3390_s23198330 crossref_primary_10_1109_ACCESS_2021_3112397 crossref_primary_10_3390_electronics9122207 crossref_primary_10_1016_j_patcog_2019_107122 crossref_primary_10_3389_fenvs_2023_1187201 crossref_primary_10_1007_s12598_024_02766_x crossref_primary_10_1109_ACCESS_2019_2938227 crossref_primary_10_1016_j_bspc_2022_103557 crossref_primary_10_1109_JBHI_2018_2871678 crossref_primary_10_1016_j_jhydrol_2015_11_011 crossref_primary_10_1007_s00521_018_3895_1 crossref_primary_10_1088_1757_899X_646_1_012027 crossref_primary_10_1159_000501951 crossref_primary_10_1016_j_eswa_2014_11_069 crossref_primary_10_1016_j_knosys_2020_106527 crossref_primary_10_1145_3605775 crossref_primary_10_1007_s00521_024_09587_0 crossref_primary_10_1016_j_psep_2024_08_055 crossref_primary_10_1007_s13042_018_0847_0 crossref_primary_10_3390_app12146883 crossref_primary_10_1007_s12204_023_2609_8 crossref_primary_10_3390_su141912232 crossref_primary_10_1155_2022_7682274 crossref_primary_10_1007_s10846_015_0213_3 crossref_primary_10_7717_peerj_cs_982 crossref_primary_10_1109_ACCESS_2022_3141767 crossref_primary_10_1109_JSEN_2018_2871599 crossref_primary_10_1016_j_gpb_2017_07_003 crossref_primary_10_1109_ACCESS_2020_2976601 crossref_primary_10_1287_isre_2021_1072 crossref_primary_10_1007_s00477_021_02161_3 crossref_primary_10_1016_j_dcan_2022_06_019 crossref_primary_10_1007_s10479_016_2308_z crossref_primary_10_1109_ACCESS_2022_3211306 crossref_primary_10_1109_TSMC_2017_2705582 crossref_primary_10_5194_hess_26_1727_2022 crossref_primary_10_1016_j_isprsjprs_2021_02_008 crossref_primary_10_3390_app9152980 crossref_primary_10_1016_j_isatra_2022_02_018 crossref_primary_10_1016_j_artmed_2022_102332 crossref_primary_10_1016_j_rse_2019_111599 crossref_primary_10_1145_3649448 crossref_primary_10_1016_j_enbuild_2020_110520 crossref_primary_10_1016_j_asoc_2014_12_034 crossref_primary_10_1016_j_engfailanal_2022_106791 crossref_primary_10_14778_3342263_3342648 crossref_primary_10_1364_OE_389231 crossref_primary_10_1109_TIE_2018_2851977 crossref_primary_10_1016_j_eswa_2019_113119 crossref_primary_10_1016_j_trac_2024_117656 crossref_primary_10_1007_s13369_024_09821_w crossref_primary_10_1007_s11548_018_1860_1 crossref_primary_10_1016_j_asoc_2023_110314 crossref_primary_10_3390_s17020403 crossref_primary_10_1177_0309524X221076976 crossref_primary_10_1007_s10723_020_09510_6 crossref_primary_10_2200_S00914ED2V01Y201904SPR017 crossref_primary_10_1093_sleep_zsae184 crossref_primary_10_3390_s20030874 crossref_primary_10_1109_ACCESS_2019_2949740 crossref_primary_10_1109_TIV_2019_2960946 crossref_primary_10_1155_2020_1496973 crossref_primary_10_1587_transcom_2017EBP3219 crossref_primary_10_3390_math9202574 crossref_primary_10_1109_ACCESS_2021_3064854 crossref_primary_10_1002_cpe_4184 crossref_primary_10_1016_j_asoc_2018_04_024 crossref_primary_10_1007_s11332_019_00557_x crossref_primary_10_3390_app9081526 crossref_primary_10_1142_S0218539319500293 crossref_primary_10_1049_itr2_12570 crossref_primary_10_1007_s00466_023_02403_x crossref_primary_10_1016_j_procs_2017_09_066 crossref_primary_10_1088_1757_899X_383_1_012018 crossref_primary_10_1016_j_neucom_2021_07_054 crossref_primary_10_1002_isaf_1488 crossref_primary_10_1016_j_eswa_2018_03_056 crossref_primary_10_1155_2021_5360828 crossref_primary_10_1016_j_psep_2021_10_036 crossref_primary_10_1093_forestry_cpy034 crossref_primary_10_1109_TSMC_2020_2964519 crossref_primary_10_1109_TCYB_2024_3498100 crossref_primary_10_2355_isijinternational_ISIJINT_2024_098 crossref_primary_10_57062_ijpem_st_2023_0115 crossref_primary_10_3390_info11010002 crossref_primary_10_1016_j_buildenv_2021_108498 crossref_primary_10_1109_MAP_2020_3043469 crossref_primary_10_1109_TII_2022_3172902 crossref_primary_10_1016_j_cie_2021_107371 crossref_primary_10_3390_en16052153 crossref_primary_10_1155_2021_8829403 crossref_primary_10_1109_TCSVT_2020_3035824 crossref_primary_10_3390_en11051040 crossref_primary_10_1016_j_eswa_2018_11_023 crossref_primary_10_1007_s10844_019_00582_9 crossref_primary_10_1016_j_ymssp_2020_107322 crossref_primary_10_1016_j_aej_2020_05_037 crossref_primary_10_3390_s17020319 crossref_primary_10_1016_j_eswa_2022_117704 crossref_primary_10_1155_2016_5642856 crossref_primary_10_1007_s10064_024_03941_1 crossref_primary_10_1016_j_resourpol_2021_102189 crossref_primary_10_1109_ACCESS_2021_3053864 crossref_primary_10_1002_cite_202200224 crossref_primary_10_1007_s11783_024_1768_7 crossref_primary_10_1186_s13673_019_0177_6 crossref_primary_10_1016_j_apenergy_2020_115402 crossref_primary_10_1016_j_trc_2020_102763 crossref_primary_10_1080_02664763_2021_1936468 crossref_primary_10_3390_rs8040329 crossref_primary_10_3390_s22197177 crossref_primary_10_3390_su151310543 crossref_primary_10_1080_24725854_2019_1632502 crossref_primary_10_1016_j_medengphy_2016_12_011 crossref_primary_10_1177_1932296819881452 crossref_primary_10_1145_3478088 crossref_primary_10_1016_j_eswa_2020_114095 crossref_primary_10_1109_ACCESS_2019_2898028 crossref_primary_10_1109_TGRS_2019_2945719 crossref_primary_10_3390_s21196666 crossref_primary_10_1016_j_engappai_2017_07_007 crossref_primary_10_3390_s19061333 crossref_primary_10_7717_peerj_cs_1076 crossref_primary_10_1002_nme_6593 crossref_primary_10_1061__ASCE_EM_1943_7889_0001556 crossref_primary_10_1155_2019_7816154 crossref_primary_10_3390_e26040311 crossref_primary_10_3390_app9020226 crossref_primary_10_1016_j_eswa_2019_113042 crossref_primary_10_1155_2019_7410701 crossref_primary_10_1155_2022_7025338 crossref_primary_10_1016_j_patcog_2020_107298 crossref_primary_10_3390_a15070252 crossref_primary_10_1016_j_imavis_2019_06_010 crossref_primary_10_1016_j_neuri_2021_100037 crossref_primary_10_29375_25392115_3718 crossref_primary_10_3390_a9040070 crossref_primary_10_1016_j_oceaneng_2021_109559 crossref_primary_10_1109_TAFFC_2021_3114365 crossref_primary_10_1016_j_neucom_2015_07_113 crossref_primary_10_1051_matecconf_202030903037 crossref_primary_10_1093_plphys_kiab322 crossref_primary_10_1109_TKDE_2020_3035685 crossref_primary_10_1007_s43069_021_00079_8 crossref_primary_10_1142_S2424786322500141 crossref_primary_10_34133_2020_4261965 crossref_primary_10_1093_cercor_bhac155 crossref_primary_10_1016_j_snb_2019_126690 crossref_primary_10_1520_SSMS20190039 crossref_primary_10_1088_1741_2552_aaf12e crossref_primary_10_1109_TSG_2023_3237011 crossref_primary_10_1109_ACCESS_2019_2936564 crossref_primary_10_3390_s19051223 crossref_primary_10_3390_app11136238 crossref_primary_10_1016_j_advwatres_2020_103622 crossref_primary_10_1016_j_asoc_2019_105970 crossref_primary_10_1016_j_eswa_2022_118962 crossref_primary_10_1016_j_patcog_2018_03_026 crossref_primary_10_1016_j_energy_2021_120100 crossref_primary_10_1016_j_ast_2018_07_024 crossref_primary_10_1016_j_enbuild_2022_112242 crossref_primary_10_1002_cepa_2184 crossref_primary_10_1038_s41598_019_55320_6 crossref_primary_10_1007_s11276_020_02250_1 crossref_primary_10_1016_j_comcom_2021_10_036 crossref_primary_10_3390_su12083103 crossref_primary_10_1016_j_neucom_2016_12_039 crossref_primary_10_1007_s00500_019_03856_0 crossref_primary_10_1016_j_compchemeng_2019_05_011 crossref_primary_10_1016_j_ijleo_2019_163675 crossref_primary_10_1038_s41698_019_0104_3 crossref_primary_10_1002_cjoc_202000393 crossref_primary_10_1177_0361198119849059 crossref_primary_10_3390_jmse8090713 crossref_primary_10_1016_j_ins_2018_10_026 crossref_primary_10_1021_acs_jpclett_2c00576 crossref_primary_10_1007_s13246_021_01013_2 crossref_primary_10_1007_s13278_021_00805_4 crossref_primary_10_1016_j_apmrv_2023_09_001 crossref_primary_10_1051_ro_2023029 crossref_primary_10_1007_s00740_021_00424_x crossref_primary_10_1155_2019_6862031 crossref_primary_10_1016_j_patrec_2019_03_018 crossref_primary_10_3390_app8081286 crossref_primary_10_1117_1_JMI_7_1_012706 crossref_primary_10_3390_s19122690 crossref_primary_10_1109_TMM_2020_2987693 crossref_primary_10_1002_sta4_294 crossref_primary_10_1016_j_heliyon_2024_e27860 crossref_primary_10_1007_s10515_021_00319_5 crossref_primary_10_1007_s11704_019_8395_7 crossref_primary_10_1016_j_compchemeng_2022_107884 crossref_primary_10_1109_JBHI_2020_2991043 crossref_primary_10_1109_TNNLS_2016_2551940 crossref_primary_10_1063_1_5095060 crossref_primary_10_1016_j_asoc_2020_106068 crossref_primary_10_1016_j_neunet_2023_03_038 crossref_primary_10_1002_isaf_1404 crossref_primary_10_1007_s00521_023_08798_1 crossref_primary_10_1016_j_ic_2024_105209 crossref_primary_10_1042_BCJ20210535 crossref_primary_10_1002_isaf_1408 crossref_primary_10_1021_acs_chemrev_2c00061 crossref_primary_10_1007_s00170_021_07784_y crossref_primary_10_1109_ACCESS_2018_2872796 crossref_primary_10_1109_ACCESS_2020_3011060 crossref_primary_10_1016_j_comnet_2019_01_019 crossref_primary_10_1007_s10614_024_10583_8 crossref_primary_10_1016_j_jprocont_2022_08_003 crossref_primary_10_1016_j_neucom_2018_03_074 crossref_primary_10_4258_hir_2018_24_3_170 crossref_primary_10_1080_10705511_2023_2169698 crossref_primary_10_47000_tjmcs_897631 crossref_primary_10_54097_ijeh_v9i2_9584 crossref_primary_10_1016_j_patrec_2020_06_006 crossref_primary_10_1109_JSTARS_2016_2608358 crossref_primary_10_1155_2018_1350692 crossref_primary_10_1016_j_asoc_2017_12_022 crossref_primary_10_1016_j_asoc_2021_107443 crossref_primary_10_1007_s00117_019_00624_x crossref_primary_10_1109_ACCESS_2020_3038314 crossref_primary_10_1016_j_future_2017_10_004 crossref_primary_10_1109_TBME_2019_2898871 crossref_primary_10_1007_s11227_020_03603_5 crossref_primary_10_1109_JIOT_2023_3243391 crossref_primary_10_1016_j_compchemeng_2025_109097 crossref_primary_10_1016_j_neunet_2023_06_033 crossref_primary_10_1016_j_cmpb_2021_106116 crossref_primary_10_1002_int_22370 crossref_primary_10_1073_pnas_2403771121 crossref_primary_10_1109_ACCESS_2020_3041600 crossref_primary_10_1016_j_neucom_2020_03_009 crossref_primary_10_1109_ACCESS_2021_3131274 crossref_primary_10_4316_AECE_2020_02005 crossref_primary_10_1016_j_ins_2016_01_082 crossref_primary_10_1038_s41598_018_35044_9 crossref_primary_10_1016_j_artmed_2020_101999 crossref_primary_10_3390_electronics8030292 crossref_primary_10_1007_s11042_019_08453_9 crossref_primary_10_1049_iet_cvi_2016_0355 crossref_primary_10_3934_mbe_2023046 crossref_primary_10_1016_j_ymssp_2020_107181 crossref_primary_10_4236_jdaip_2020_83012 crossref_primary_10_1002_widm_1430 crossref_primary_10_1016_j_cageo_2020_104461 crossref_primary_10_1016_j_ins_2021_12_061 crossref_primary_10_1063_1_5088533 crossref_primary_10_1016_j_patcog_2017_10_017 crossref_primary_10_1016_j_apergo_2021_103574 crossref_primary_10_1021_acs_jcim_9b00266 crossref_primary_10_3390_s20041158 crossref_primary_10_3390_app10072522 crossref_primary_10_3233_JIFS_169527 crossref_primary_10_1016_j_eswa_2020_114527 crossref_primary_10_1145_3450963 crossref_primary_10_1016_j_artint_2019_103176 crossref_primary_10_1109_THMS_2019_2938156 crossref_primary_10_1063_5_0134464 crossref_primary_10_1016_j_cmpb_2021_106121 crossref_primary_10_1016_j_eswa_2019_112896 crossref_primary_10_1016_j_mlwa_2023_100517 crossref_primary_10_1111_mice_13311 crossref_primary_10_1016_j_optlastec_2025_112450 crossref_primary_10_1007_s10462_023_10443_1 crossref_primary_10_1016_j_cogr_2021_07_001 crossref_primary_10_1016_j_ijmedinf_2023_105004 crossref_primary_10_3389_fnhum_2020_00365 crossref_primary_10_1007_s10586_024_04684_0 crossref_primary_10_1115_1_4037435 crossref_primary_10_1002_er_4855 crossref_primary_10_3390_w15193427 crossref_primary_10_1016_j_patcog_2021_108490 crossref_primary_10_1016_j_patcog_2019_106973 crossref_primary_10_1016_j_coisb_2021_04_009 crossref_primary_10_3389_fphys_2019_01554 crossref_primary_10_1007_s40843_024_2851_9 crossref_primary_10_1016_j_ecoinf_2021_101237 crossref_primary_10_1007_s12028_022_01449_8 crossref_primary_10_1016_j_jclepro_2024_144287 crossref_primary_10_1109_TETC_2022_3143154 crossref_primary_10_1038_s41598_020_76129_8 crossref_primary_10_1371_journal_pone_0119044 crossref_primary_10_1109_ACCESS_2019_2910239 crossref_primary_10_1109_JIOT_2022_3213892 crossref_primary_10_1186_s12918_018_0626_2 crossref_primary_10_3390_su15010272 crossref_primary_10_1115_1_4056287 crossref_primary_10_1109_TEVC_2019_2925722 crossref_primary_10_1061__ASCE_CP_1943_5487_0000797 crossref_primary_10_3390_jlpea13020039 crossref_primary_10_1109_ACCESS_2020_3035347 crossref_primary_10_1109_ACCESS_2021_3097614 crossref_primary_10_1016_j_actaastro_2022_06_026 crossref_primary_10_1016_j_ijcce_2023_02_002 crossref_primary_10_1002_eng2_12739 crossref_primary_10_1109_ACCESS_2021_3064819 crossref_primary_10_1016_j_eswa_2021_114800 crossref_primary_10_3390_forecast5010017 crossref_primary_10_3233_IDA_240002 crossref_primary_10_3390_mi11070642 crossref_primary_10_1109_TR_2019_2907402 crossref_primary_10_1155_2018_8125126 crossref_primary_10_1109_TIM_2022_3212547 crossref_primary_10_1016_j_icheatmasstransfer_2016_05_031 crossref_primary_10_1007_s00034_019_01103_3 crossref_primary_10_1061__ASCE_ST_1943_541X_0002535 crossref_primary_10_1007_s11269_021_02990_5 crossref_primary_10_1007_s10586_018_2385_7 crossref_primary_10_1016_j_eswa_2020_113609 crossref_primary_10_1016_j_compag_2020_105888 crossref_primary_10_1016_j_neunet_2021_01_001 crossref_primary_10_1109_LCOMM_2020_2968902 crossref_primary_10_1007_s10489_019_01526_0 crossref_primary_10_1016_j_patrec_2020_05_019 crossref_primary_10_1109_ACCESS_2019_2942040 crossref_primary_10_1016_j_chaos_2018_06_015 crossref_primary_10_1016_j_procir_2019_03_012 crossref_primary_10_1016_j_finel_2019_103377 crossref_primary_10_1016_j_asoc_2024_112116 crossref_primary_10_3390_w12020440 crossref_primary_10_1109_ACCESS_2021_3134628 crossref_primary_10_1111_epi_13907 crossref_primary_10_3390_app9153041 crossref_primary_10_1016_j_engappai_2024_109740 crossref_primary_10_35234_fumbd_1425635 crossref_primary_10_3233_IDA_184403 crossref_primary_10_1007_s12652_022_03910_0 crossref_primary_10_3389_fenvs_2024_1445967 crossref_primary_10_1007_s10596_020_10005_2 crossref_primary_10_1186_s13073_016_0319_7 crossref_primary_10_1016_j_cogsys_2020_04_003 crossref_primary_10_1177_1687814017704146 crossref_primary_10_1016_j_jbi_2021_103694 crossref_primary_10_1016_j_knosys_2020_106081 crossref_primary_10_1080_0952813X_2022_2093407 crossref_primary_10_1109_TCSVT_2020_3042559 crossref_primary_10_1016_j_sna_2017_12_011 crossref_primary_10_1016_j_ocemod_2023_102232 crossref_primary_10_1038_s41598_024_58680_w crossref_primary_10_1016_j_knosys_2017_05_026 crossref_primary_10_3390_s18092809 crossref_primary_10_3390_make2040027 crossref_primary_10_1007_s41060_019_00177_1 crossref_primary_10_1109_ACCESS_2024_3358452 crossref_primary_10_3390_su10010085 crossref_primary_10_1002_smsc_202300306 crossref_primary_10_1016_j_ymssp_2024_111347 crossref_primary_10_1016_j_rser_2018_04_013 crossref_primary_10_2166_ws_2020_277 crossref_primary_10_2355_tetsutohagane_TETSU_2022_098 crossref_primary_10_1016_j_asoc_2017_05_011 crossref_primary_10_1016_j_neucom_2016_09_064 crossref_primary_10_1109_ACCESS_2020_3015529 crossref_primary_10_1080_17517575_2016_1218055 |
| Cites_doi | 10.1145/1553374.1553505 10.1145/1553374.1553475 10.3390/s130201578 10.1109/29.21701 10.1016/j.snb.2012.06.070 10.1145/775047.775062 10.1145/1081870.1081883 10.1364/JOSAA.20.001237 10.1007/978-3-642-21735-7_6 10.1016/j.eswa.2008.09.049 10.1007/978-3-642-04174-7_9 10.1109/JSEN.2002.800688 10.1016/S0925-4005(00)00482-2 10.1257/089533003321164958 10.1109/TKDE.2009.191 10.1088/1741-2560/8/3/036015 10.7551/mitpress/7503.003.0173 10.1162/089976602760128018 10.1162/089976602317318938 10.1016/j.snb.2007.12.032 10.1145/959242.959248 10.1109/ICASSP.2010.5495651 10.1109/ICASSP.1996.543213 10.1086/294743 10.1142/S0219622006002258 10.1016/j.jocs.2010.12.007 10.1080/10867651.1998.10487493 10.1109/72.536317 10.1016/j.conb.2005.10.011 10.1162/neco.2006.18.7.1527 10.1109/IJCNN.1999.836246 10.1162/089976600300015015 10.1145/345370.345409 10.1109/ISCAS.1991.176402 10.1145/1273496.1273619 10.1109/MSP.2012.2205597 10.1145/1273496.1273592 10.1109/TASL.2011.2109382 10.1016/S0925-2312(00)00358-1 10.1007/978-3-642-21735-7_7 10.1016/S0925-2312(98)00018-6 10.1049/ip-cds:19990670 10.1109/CVPR.2005.177 10.1162/neco.2008.04-07-510 10.1016/j.asoc.2010.09.007 10.1109/CVPR.2011.5995496 10.1126/science.1127647 10.1145/1553374.1553453 10.1016/j.eswa.2008.07.006 10.1109/ICASSP.2012.6288282 10.1109/CVPR.2010.5539773 10.1109/TSA.2004.828699 10.1109/TBME.2010.2049492 10.1016/S0925-2312(01)00706-8 10.1007/s10844-013-0248-5 10.1016/j.snb.2004.02.024 10.1007/978-3-642-15567-3_11 10.1007/s00217-005-0144-5 10.1016/j.snb.2006.12.039 10.1161/01.CIR.101.23.e215 10.1016/j.eswa.2007.06.023 10.1016/j.dss.2010.08.028 10.1109/ICCV.1999.790410 10.1162/neco.1997.9.8.1735 10.1109/TASL.2011.2134090 10.1016/S0925-4005(00)00548-7 10.1109/ICASSP.2013.6638947 10.1109/72.279181 10.1109/MASSP.1986.1165342 10.1109/CVPR.2010.5539962 10.1016/j.neuroimage.2009.08.028 10.1109/ROBOT.2001.933245 10.1162/neco.2010.01-09-953 10.1049/el:20010985 10.1016/S0925-4005(03)00574-4 |
| ContentType | Journal Article |
| Copyright | 2014 Elsevier B.V. |
| Copyright_xml | – notice: 2014 Elsevier B.V. |
| DBID | AAYXX CITATION AABEP ADTPV AOWAS D8T D91 ZZAVC ADTOC UNPAY |
| DOI | 10.1016/j.patrec.2014.01.008 |
| DatabaseName | CrossRef SWEPUB Örebro universitet full text SwePub SwePub Articles SWEPUB Freely available online SWEPUB Örebro universitet SwePub Articles full text Unpaywall for CDI: Periodical Content Unpaywall |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: UNPAY name: Unpaywall url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/ sourceTypes: Open Access Repository |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 1872-7344 |
| EndPage | 24 |
| ExternalDocumentID | oai:DiVA.org:oru-34597 oai_DiVA_org_oru_34597 10_1016_j_patrec_2014_01_008 S0167865514000221 |
| GroupedDBID | --M .DC .~1 0R~ 123 1RT 1~. 1~5 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXUO AAYFN ABBOA ABFNM ABFRF ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFO ACGFS ACRLP ACZNC ADBBV ADEZE ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD AXJTR BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ J1W JJJVA KOM LG9 LY1 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 RIG RNS ROL SDF SDG SDP SES SPC SPCBC SST SSV SSZ T5K TN5 UNMZH WH7 XPP ZMT ~G- --K 1B1 29O AAQXK AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACLOT ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADMXK ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EJD FEDTE FGOYB HLZ HVGLF HZ~ IHE R2- RPZ SBC SDS SEW VOH WUQ Y6R ~HD AABEP ADTPV AGCQF AOWAS D8T D91 ZZAVC ADTOC UNPAY |
| ID | FETCH-LOGICAL-c389t-ef7b98efc3ec05012a513e8601c3eabbe80b1b9b7988516f2f8e5cc4919efcfa3 |
| IEDL.DBID | .~1 |
| ISSN | 0167-8655 1872-7344 |
| IngestDate | Sun Oct 26 04:02:47 EDT 2025 Tue Sep 09 22:59:52 EDT 2025 Wed Oct 01 06:31:39 EDT 2025 Thu Apr 24 23:10:43 EDT 2025 Fri Feb 23 02:26:37 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Keywords | Unsupervised feature learning Deep learning Time-series |
| Language | English |
| License | other-oa |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c389t-ef7b98efc3ec05012a513e8601c3eabbe80b1b9b7988516f2f8e5cc4919efcfa3 |
| OpenAccessLink | https://proxy.k.utb.cz/login?url=http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-34597 |
| PageCount | 14 |
| ParticipantIDs | unpaywall_primary_10_1016_j_patrec_2014_01_008 swepub_primary_oai_DiVA_org_oru_34597 crossref_citationtrail_10_1016_j_patrec_2014_01_008 crossref_primary_10_1016_j_patrec_2014_01_008 elsevier_sciencedirect_doi_10_1016_j_patrec_2014_01_008 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2014-06-01 |
| PublicationDateYYYYMMDD | 2014-06-01 |
| PublicationDate_xml | – month: 06 year: 2014 text: 2014-06-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationTitle | Pattern recognition letters |
| PublicationYear | 2014 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Li, Ma (b0395) 2010; vol. 01 H. Kamyshanska, R. Memisevic, On autoencoder scoring, in: Proceedings of the 30th International Conference on Machine Learning (ICML-13), JMLR Workshop and Conference Proceedings, 2013, pp. 720–728. Dahl, Ranzato, Mohamed, Hinton (b0115) 2010; 23 Nanopoulos, Alcock, Manolopoulos (b0485) 2001; 10 Yamazaki, Ludermir, De Souto (b0650) 2001; 37 E. Keogh, S. Kasetty, On the need for time series data mining benchmarks: a survey and empirical demonstration, in: Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2002, pp. 102–111. J. Nam, J. Herrera, M. Slaney, J.O. Smith, Learning sparse feature representations for music annotation and retrieval, in: The International Society for Music Information Retrieval (ISMIR), 2012, pp. 565–570. M. Ranzato, G. Hinton, Modeling pixel means and covariances using factorized third-order Boltzmann machines, in: Proceedings of Computer Vision and Pattern Recognition Conference (CVPR 2010), 2010. G.W. Taylor, Composable, distributed-state models for high-dimensional time series (Ph.D. thesis), Department of Computer Science, University of Toronto, 2009. Osuna, Nagle, Kermani, Schiffman (b0495) 2003 D. Stavens, S. Thrun, Unsupervised learning of invariant features using video, in: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010, pp. 1649–1656. Wulsin, Gupta, Mani, Blanco, Litt (b0645) 2011; 8 M. Ranzato, A. Krizhevsky, G. Hinton, Factored 3-way restricted Boltzmann machines for modeling natural images, in: Proceedings of the International Conference on Artificial Intelligence and Statistics, 2010. Vito, Castaldo, Loffredo, Massera, Polichetti, Nasti, Vacca, Quercia, Francia (b0620) 2007; 124 S. Dieleman, P. Brakel, B. Schrauwen, Audio-based music classification with a pretrained convolutional network, in: The International Society for Music Information Retrieval (ISMIR), 2011. K. Chang, J. Jang, C. Iliopoulos, Music genre classification via compressive sampling, in: Proceedings of the 11th International Conference on Music Information Retrieval (ISMIR), 2010, pp. 387–392. Mirowski, LeCun, Madhavan, Kuzniecky (b0460) 2008 Sutskever, Hinton, Taylor (b0575) 2008 transform toolbox for music processing, in: Seventh Sound and Music Computing Conference, 2010. A. Saxe, P. Koh, Z. Chen, M. Bhand, B. Suresh, A.Y. Ng, On random weights and unsupervised feature learning, in: Proceedings of the 28th International Conference on Machine Learning, 2011. Dahl, Yu, Deng, Acero (b0110) 2012; 20 Jaitly, Hinton (b0305) 2011 . Atsalakis, Valavanis (b0015) 2009; 36 Lafferty, McCallum, Pereira (b0340) 2001 R. Pascanu, T. Mikolov, Y. Bengio, Understanding the exploding gradient problem, Computing Research Repository (CoRR) abs/1211.5063, 2012. Hinton (b0250) 2002; 14 J. Nam, Learning feature representations for music classification (Ph.D. thesis), Stanford University, 2012. T. Duckett, M. Axelsson, A. Saffiotti, Learning to locate an odour source with a mobile robot, in: IEEE International Conference on Robotics and Automation, 2001. Proceedings 2001 ICRA, vol. 4, 2001, pp. 4017–4022. LeCun, Kavukvuoglu, Farabet (b0375) 2010 Hinton, Osindero, Teh (b0265) 2006; 18 Goldberger, Amaral, Glass, Hausdorff, Ivanov, Mark, Mietus, Moody, Peng, Stanley (b0195) 2000; 101 Zhang, Balaban, Principe (b0665) 2003; 96 W. Pan, L. Torresani, Unsupervised hierarchical modeling of locomotion styles, in: Proceedings of the 26th Annual International Conference on Machine Learning, 2009, pp. 785–792. Trincavelli, Coradeschi, Loutfi, Söderquist, Thunberg (b0600) 2010; 57 Bengio, Lamblin, Popovici, Larochelle (b0035) 2007; 19 Kavukcuoglu, Ranzato, Fergus, Le-Cun (b0325) 2009 I. Sutskever, Training recurrent neural networks (Ph.D. thesis), University of Toronto, 2012. Pan, Yang (b0310) 2010; 22 Längkvist, Coradeschi, Loutfi, Rayappan (b0345) 2013; 13 W.Y. Zou, A.Y. Ng, K. Yu, Unsupervised learning of visual invariance with temporal coherence, in: NIPS 2011 Workshop on Deep Learning and Unsupervised Feature Learning, 2011. Carmona, Martinez, Zalacain, Rodriguez-Mendez, de Saja, Alonso (b0085) 2006; 223 Hyvärinen, Ramkumar, Parkkonen, Hari (b0295) 2010; 49 Memisevic, Hinton (b0440) 2007 Bennetts, Lilienthal, Neumann, Trincavelli (b0055) 2011; 4 Gleicher (b0190) 2000; 33 Luenberger (b0410) 1979 Furui, Kikuchi, Shinnaka, Hori (b0160) 2004; 12 Gers, Schmidhuber, Cummins (b0185) 2000; 12 Hinton, Salakhutdinov (b0245) 2006; 313 Kim (b0335) 1998; 20 C. Tucker, Self-organizing maps for time series analysis of electromyographic data, in: International Joint Conference on Neural Networks, 1999. IJCNN ’99, 1999, pp. 3577–3580. E. Parris, M. Carey, Language independent gender identification, in: 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings, vol. 2, 1996, pp. 685–688. Humphrey, Bello, LeCun (b0280) 2013; 41 M. Sugiyama, H. Sawai, A. Waibel, Review of tdnn (time delay neural network) architectures for speech recognition, in: IEEE International Sympoisum on Circuits and Systems, vol. 1, 1991, pp. 582–585. Gärtner (b0180) 2003; 5 Hines, Llobet, Gardner (b0235) 1999; 146 Grassia (b0200) 1998; 3 T. van Kasteren, A. Noulas, B. Kröse, Conditional random fields versus hidden markov models for activity recognition in temporal sensor data, in: Proceedings of the 14th Annual Conference of the Advanced School for Computing and Imaging (ASCI’08), The Netherlands, 2008. M. Längkvist, A. Loutfi, Not all signals are created equal: dynamic objective auto-encoder for multivariate data, in: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2012. Hsieh, Hsiao, Yeh (b0275) 2011; 11 D. Lowe, Object recognition from local scale-invariant features, in: ICCV, 1999. Hyvèarinen, Hurri, Hoyer (b0300) 2009; vol. 39 Lütkepohl (b0415) 2005 Zampolli, Elmi, Ahmed, Passini, Cardinali, Nicoletti, Dori (b0660) 2004; 101 R. Grosse, R. Raina, H. Kwong, A.Y. Ng, Shift-invariant sparse coding for audio classification, in: Conference on Uncertainty in Artificial Intelligence (UAI), 2007. G. Taylor, G. Hinton, Factored conditional restricted Boltzmann machines for modeling motion style, in: Proceedings of the 26th International Conference on Machine Learning (ICML), 2009. Q.V. Le, W.Y. Zou, S.Y. Yeung, A.Y. Ng, Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis, in: Computer Vision and Pattern Recognition (CVPR), 2011. Gardner, Shin, Hines (b0170) 2000; 70 K. Markov, T. Matsui, Music genre classification using self-taught learning via sparse coding, in: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012, pp. 1929–1932. Yang, Wu (b0655) 2006; 05 Dutta, Hines, Gardner, Boilot (b0140) 2002; 1 Mirowski, LeCun (b0450) 2009 Agrawal, Chourasia, Mittra (b0005) 2013; 2 Martens, Sutskever (b0430) 2012; vol. 7700 Hyvärinen, Hurri, Väyrynen (b0290) 2003; 20 Rabiner, Juang (b0515) 1986; 3 M. Henaff, K. Jarrett, K. Kavukcuoglu, Y. LeCun, Unsupervised learning of sparse features for scalable audio classification, in: Proceedings of International Symposium on Music, Information Retrieval (ISMIR’11), 2011. N. Dalal, B. Triggs, Histograms of oriented gradients for human detection, in: CVPR, 2005. Y. Bengio, A. Courville, P. Vincent, Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives. Technical Report, U. Montreal, 2012. Available from P. Mirowski, D. Madhavan, Y. LeCun, Time-delay neural networks and independent component analysis for eeg-based prediction of epileptic seizures propagation, in: Association for the Advancement of Artificial Intelligence Conference, 2007. G.E. Hinton, A. Krizhevsky, S.D. Wang, Transforming auto-encoders, in: Proceedings of the 21th International Conference on Artificial Neural Networks, vol. Part I, 2011, pp. 44–51. Y. Bengio, L. Yao, G. Alain, P. Vincent, Generalized denoising auto-encoders as generative models. CoRR abs/1305.6663, 2013. Lee, Largman, Pham, Ng (b0390) 2009; 22 Gardner, Bartlett (b0165) 1999 A. Graves, A. Mohamed, G. Hinton, Speech recognition with deep recurrent neural networks, in: The 38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2013. Bengio, LeCun (b0040) 2007 P. Hamel, D. Eck, Learning features from music audio with deep belief networks, in: 11th International Society for Music Information Retrieval Conference (ISMIR), 2010. A. Mohamed, G. Hinton, Phone recognition using restricted Boltzmann machines, in: 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2010, pp. 4354–4357. G. Taylor, G.E. Hinton, S. Roweis, Modeling human motion using binary latent variables, in: Advances in Neural Information Processing Systems, 2007. Tsai, Hsiao (b0605) 2010; 50 H. Lee, R. Grosse, R. Ranganath, A.Y. Ng, Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations, in: 26th International Conference on Machine Learning, 2009. J.M. Wang, D.J. Fleet, A. Hertzmann, Multi-factor Gaussian process models for style-content separation, in: International Conference of Machine Learning (ICML), 2007, pp. 975–982. Hüsken, Stagge (b0285) 2003; 50 Gardner, Shin, Hines, Dow (b0175) 2000; 69 Bhattacharya, Tudu, Jana, Ghosh, Bandhopadhyaya, Bhuyan (b0060) 2008; 131 Memisevic, Hinton (b0445) 2010; 22 R. Raina, A. Battle, H. Lee, B. Packer, A.Y. Ng, Self-taught learning: transfer learning from unlabeled data, in: Proceedings of the 24th International Conference on Machine Learning, 2007. Bengio, Simard, Frasconi (b0045) 1994; 5 Längkvist, Karlsson, Loutfi (b0350) 2012; 2012 Hinton (b0255) 2010; vol. 7700 Hochreiter, Schmidhuber (b0270) 1997; 9 Brand, Hertzmann (b0080) 2000 J. Ngiam, A. Khosla, M. Kim, J. Nam, H. Lee, A.Y. Ng, Multimodal deep learning, in: Proceedings of the 28th International Conference on Machine Learning, 2011. C. Schoerkhuber, A. Klapuri, Constant- Y. Bengio, Learning Deep Architectures for AI. Technical Report 1312. Dept. IRO, U 10.1016/j.patrec.2014.01.008_b0100 10.1016/j.patrec.2014.01.008_b0585 10.1016/j.patrec.2014.01.008_b0065 10.1016/j.patrec.2014.01.008_b0500 10.1016/j.patrec.2014.01.008_b0225 Carmona (10.1016/j.patrec.2014.01.008_b0085) 2006; 223 Dutta (10.1016/j.patrec.2014.01.008_b0140) 2002; 1 Lin (10.1016/j.patrec.2014.01.008_b0400) 2009; 36 Ranzato (10.1016/j.patrec.2014.01.008_b0535) 2006 10.1016/j.patrec.2014.01.008_b0580 Nanopoulos (10.1016/j.patrec.2014.01.008_b0485) 2001; 10 Gutierrez-Osuna (10.1016/j.patrec.2014.01.008_b0220) 2002; 2 Hochreiter (10.1016/j.patrec.2014.01.008_b0270) 1997; 9 Sutskever (10.1016/j.patrec.2014.01.008_b0575) 2008 Bengio (10.1016/j.patrec.2014.01.008_b0035) 2007; 19 Wang (10.1016/j.patrec.2014.01.008_b0630) 2013; 3 Malkiel (10.1016/j.patrec.2014.01.008_b0420) 2003; 17 Hüsken (10.1016/j.patrec.2014.01.008_b0285) 2003; 50 Trincavelli (10.1016/j.patrec.2014.01.008_b0600) 2010; 57 Gardner (10.1016/j.patrec.2014.01.008_b0170) 2000; 70 10.1016/j.patrec.2014.01.008_b0215 Hines (10.1016/j.patrec.2014.01.008_b0235) 1999; 146 10.1016/j.patrec.2014.01.008_b0475 Bottou (10.1016/j.patrec.2014.01.008_b0075) 2010 10.1016/j.patrec.2014.01.008_b0355 10.1016/j.patrec.2014.01.008_b0230 10.1016/j.patrec.2014.01.008_b0510 10.1016/j.patrec.2014.01.008_b0595 Dahl (10.1016/j.patrec.2014.01.008_b0115) 2010; 23 Flash (10.1016/j.patrec.2014.01.008_b0155) 2005; 15 10.1016/j.patrec.2014.01.008_b0590 Zhu (10.1016/j.patrec.2014.01.008_b0670) 2008; 34 Hinton (10.1016/j.patrec.2014.01.008_b0245) 2006; 313 10.1016/j.patrec.2014.01.008_b0470 Kim (10.1016/j.patrec.2014.01.008_b0335) 1998; 20 10.1016/j.patrec.2014.01.008_b0505 Brand (10.1016/j.patrec.2014.01.008_b0080) 2000 Yamazaki (10.1016/j.patrec.2014.01.008_b0650) 2001; 37 Mirowski (10.1016/j.patrec.2014.01.008_b0450) 2009 Atsalakis (10.1016/j.patrec.2014.01.008_b0015) 2009; 36 10.1016/j.patrec.2014.01.008_b0365 Smith (10.1016/j.patrec.2014.01.008_b0550) 2005 10.1016/j.patrec.2014.01.008_b0520 10.1016/j.patrec.2014.01.008_b0120 Furui (10.1016/j.patrec.2014.01.008_b0160) 2004; 12 Längkvist (10.1016/j.patrec.2014.01.008_b0345) 2013; 13 Zhang (10.1016/j.patrec.2014.01.008_b0665) 2003; 96 10.1016/j.patrec.2014.01.008_b0125 Vembu (10.1016/j.patrec.2014.01.008_b0615) 2012; 174 Vito (10.1016/j.patrec.2014.01.008_b0620) 2007; 124 Gärtner (10.1016/j.patrec.2014.01.008_b0180) 2003; 5 10.1016/j.patrec.2014.01.008_b0480 10.1016/j.patrec.2014.01.008_b0360 Lafferty (10.1016/j.patrec.2014.01.008_b0340) 2001 Kavukcuoglu (10.1016/j.patrec.2014.01.008_b0325) 2009 Gardner (10.1016/j.patrec.2014.01.008_b0165) 1999 Hyvèarinen (10.1016/j.patrec.2014.01.008_b0300) 2009; vol. 39 10.1016/j.patrec.2014.01.008_b0635 10.1016/j.patrec.2014.01.008_b0530 Bollen (10.1016/j.patrec.2014.01.008_b0070) 2011; 2 Jaitly (10.1016/j.patrec.2014.01.008_b0305) 2011 Agrawal (10.1016/j.patrec.2014.01.008_b0005) 2013; 2 Wulsin (10.1016/j.patrec.2014.01.008_b0645) 2011; 8 10.1016/j.patrec.2014.01.008_b0135 Osuna (10.1016/j.patrec.2014.01.008_b0495) 2003 10.1016/j.patrec.2014.01.008_b0490 10.1016/j.patrec.2014.01.008_b0090 Dahl (10.1016/j.patrec.2014.01.008_b0110) 2012; 20 Dietterich (10.1016/j.patrec.2014.01.008_b0130) 2002 Zampolli (10.1016/j.patrec.2014.01.008_b0660) 2004; 101 Amft (10.1016/j.patrec.2014.01.008_b0010) 2011 Fama (10.1016/j.patrec.2014.01.008_b0150) 1965; 1 Memisevic (10.1016/j.patrec.2014.01.008_b0440) 2007 10.1016/j.patrec.2014.01.008_b0525 10.1016/j.patrec.2014.01.008_b0405 Tsai (10.1016/j.patrec.2014.01.008_b0605) 2010; 50 Li (10.1016/j.patrec.2014.01.008_b0395) 2010; vol. 01 10.1016/j.patrec.2014.01.008_b0020 Luenberger (10.1016/j.patrec.2014.01.008_b0410) 1979 10.1016/j.patrec.2014.01.008_b0025 10.1016/j.patrec.2014.01.008_b0385 Yang (10.1016/j.patrec.2014.01.008_b0655) 2006; 05 10.1016/j.patrec.2014.01.008_b0540 Lee (10.1016/j.patrec.2014.01.008_b0380) 2008; 20 10.1016/j.patrec.2014.01.008_b0260 Hsieh (10.1016/j.patrec.2014.01.008_b0275) 2011; 11 Hinton (10.1016/j.patrec.2014.01.008_b0250) 2002; 14 Memisevic (10.1016/j.patrec.2014.01.008_b0445) 2010; 22 Le Roux (10.1016/j.patrec.2014.01.008_b0370) 2008; 20 Cheung (10.1016/j.patrec.2014.01.008_b0095) 2001; 41 Bengio (10.1016/j.patrec.2014.01.008_b0045) 1994; 5 Rabiner (10.1016/j.patrec.2014.01.008_b0515) 1986; 3 Wiskott (10.1016/j.patrec.2014.01.008_b0640) 2002; 14 10.1016/j.patrec.2014.01.008_b0675 Bhattacharya (10.1016/j.patrec.2014.01.008_b0060) 2008; 131 10.1016/j.patrec.2014.01.008_b0555 Coates (10.1016/j.patrec.2014.01.008_b0105) 2010 Grassia (10.1016/j.patrec.2014.01.008_b0200) 1998; 3 Pan (10.1016/j.patrec.2014.01.008_b0310) 2010; 22 Gardner (10.1016/j.patrec.2014.01.008_b0175) 2000; 69 Gleicher (10.1016/j.patrec.2014.01.008_b0190) 2000; 33 Bennetts (10.1016/j.patrec.2014.01.008_b0055) 2011; 4 Martens (10.1016/j.patrec.2014.01.008_b0430) 2012; vol. 7700 Lütkepohl (10.1016/j.patrec.2014.01.008_b0415) 2005 10.1016/j.patrec.2014.01.008_b0545 10.1016/j.patrec.2014.01.008_b0425 Längkvist (10.1016/j.patrec.2014.01.008_b0350) 2012; 2012 10.1016/j.patrec.2014.01.008_b0565 10.1016/j.patrec.2014.01.008_b0560 Hyvärinen (10.1016/j.patrec.2014.01.008_b0290) 2003; 20 10.1016/j.patrec.2014.01.008_b0320 Waibel (10.1016/j.patrec.2014.01.008_b0625) 1989; 37 Gers (10.1016/j.patrec.2014.01.008_b0185) 2000; 12 Bengio (10.1016/j.patrec.2014.01.008_b0030) 1996; 7 Bengio (10.1016/j.patrec.2014.01.008_b0040) 2007 Hinton (10.1016/j.patrec.2014.01.008_b0255) 2010; vol. 7700 Hinton (10.1016/j.patrec.2014.01.008_b0265) 2006; 18 10.1016/j.patrec.2014.01.008_b0435 10.1016/j.patrec.2014.01.008_b0315 10.1016/j.patrec.2014.01.008_b0210 Mirowski (10.1016/j.patrec.2014.01.008_b0460) 2008 10.1016/j.patrec.2014.01.008_b0455 10.1016/j.patrec.2014.01.008_b0610 Goldberger (10.1016/j.patrec.2014.01.008_b0195) 2000; 101 10.1016/j.patrec.2014.01.008_b0570 Hinton (10.1016/j.patrec.2014.01.008_b0240) 2012; 29 10.1016/j.patrec.2014.01.008_b0330 LeCun (10.1016/j.patrec.2014.01.008_b0375) 2010 Lee (10.1016/j.patrec.2014.01.008_b0390) 2009; 22 Hyvärinen (10.1016/j.patrec.2014.01.008_b0295) 2010; 49 Erhan (10.1016/j.patrec.2014.01.008_b0145) 2010; 11 10.1016/j.patrec.2014.01.008_b0050 Humphrey (10.1016/j.patrec.2014.01.008_b0280) 2013; 41 Mohamed (10.1016/j.patrec.2014.01.008_b0465) 2012; 20 10.1016/j.patrec.2014.01.008_b0205 |
| References_xml | – reference: G. Taylor, R. Fergus, Y. LeCun, C. Bregler, Convolutional learning of spatio-temporal features, in: Proceedings European Conference on Computer Vision (ECCV’10), 2010. – volume: 18 start-page: 1527 year: 2006 end-page: 1554 ident: b0265 article-title: A fast learning algorithm for deep belief nets publication-title: Neural Comput. – volume: 2 start-page: 1 year: 2011 end-page: 8 ident: b0070 article-title: Twitter mood predicts the stock market publication-title: J. Comput. Sci. – reference: J. Masci, U. Meier, D. Cireşan, J. Schmidhuber, Stacked convolutional auto-encoders for hierarchical feature extraction, in: Proceedings of the 21th International Conference on Artificial Neural Networks, vol. Part I, 2011, pp. 52–59. – year: 2010 ident: b0375 article-title: Convolutional networks and applications in vision publication-title: Proceedings International Symposium on Circuits and Systems (ISCASąŕ10) – volume: 36 start-page: 7313 year: 2009 end-page: 7317 ident: b0400 article-title: Short-term stock price prediction based on echo state networks publication-title: Expert Syst. Appl. – reference: R. Grosse, R. Raina, H. Kwong, A.Y. Ng, Shift-invariant sparse coding for audio classification, in: Conference on Uncertainty in Artificial Intelligence (UAI), 2007. – volume: 29 start-page: 82 year: 2012 end-page: 97 ident: b0240 article-title: Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups publication-title: IEEE Signal Proc. Mag. – volume: 2012 year: 2012 ident: b0350 article-title: Sleep stage classification using unsupervised feature learning publication-title: Adv. Artif. Neural Syst. – year: 2005 ident: b0550 article-title: Learning efficient auditory codes using spikes predicts cochlear filters publication-title: Advances in Neural Information Processing Systems – volume: 3 start-page: 4 year: 1986 end-page: 16 ident: b0515 article-title: An introduction to hidden Markov models publication-title: IEEE ASSP Mag. – start-page: 1 year: 2007 end-page: 8 ident: b0440 article-title: Unsupervised learning of image transformations publication-title: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – volume: 41 start-page: 145 year: 2001 end-page: 152 ident: b0095 article-title: Independent component ordering in ica time series analysis publication-title: Neurocomputing – reference: C. Schoerkhuber, A. Klapuri, Constant- – start-page: 282 year: 2001 end-page: 289 ident: b0340 article-title: Conditional random fields: probabilistic models for segmenting and labeling sequence data publication-title: Proceedings of the 18th International Conference on Machine Learning – volume: 14 start-page: 1771 year: 2002 end-page: 1800 ident: b0250 article-title: Training products of experts by minimizing contrastive divergence publication-title: Neural Comput. – year: 2003 ident: b0495 article-title: Signal Conditioning and Preprocessing publication-title: HandBook of Machine Olfaction, Electronic Nose Technology – reference: J. Nam, J. Herrera, M. Slaney, J.O. Smith, Learning sparse feature representations for music annotation and retrieval, in: The International Society for Music Information Retrieval (ISMIR), 2012, pp. 565–570. – reference: M. Sugiyama, H. Sawai, A. Waibel, Review of tdnn (time delay neural network) architectures for speech recognition, in: IEEE International Sympoisum on Circuits and Systems, vol. 1, 1991, pp. 582–585. – reference: P. Mirowski, D. Madhavan, Y. LeCun, Time-delay neural networks and independent component analysis for eeg-based prediction of epileptic seizures propagation, in: Association for the Advancement of Artificial Intelligence Conference, 2007. – start-page: 1601 year: 2008 end-page: 1608 ident: b0575 article-title: The recurrent temporal restricted Boltzmann machine publication-title: Adv. Neural Inf. Process. Syst. – reference: Y. Bengio, L. Yao, G. Alain, P. Vincent, Generalized denoising auto-encoders as generative models. CoRR abs/1305.6663, 2013. – volume: 57 start-page: 2884 year: 2010 end-page: 2890 ident: b0600 article-title: Direct identification of bacteria in blood culture samples using an electronic nose publication-title: IEEE Trans. Biomed. Eng. – volume: 37 start-page: 328 year: 1989 end-page: 339 ident: b0625 article-title: Phoneme recognition using time-delay neural networks publication-title: IEEE Trans. Acoust. Speech Signal Process. – reference: A. Graves, A. Mohamed, G. Hinton, Speech recognition with deep recurrent neural networks, in: The 38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2013. – volume: 9 start-page: 1735 year: 1997 end-page: 1780 ident: b0270 article-title: Long short-term memory publication-title: Neural Comput. – reference: J. Ngiam, A. Khosla, M. Kim, J. Nam, H. Lee, A.Y. Ng, Multimodal deep learning, in: Proceedings of the 28th International Conference on Machine Learning, 2011. – year: 2005 ident: b0415 article-title: New Introduction to Multiple Time Series Analysis – volume: 1 start-page: 34 year: 1965 end-page: 105 ident: b0150 article-title: The behavior of stock-market prices publication-title: J. Bus. – volume: 96 start-page: 385 year: 2003 end-page: 389 ident: b0665 article-title: Improving pattern recognition of electronic nose data with time-delay neural networks publication-title: Sens. Actuators B: Chem. – reference: M. Längkvist, A. Loutfi, Unsupervised feature learning for electronic nose data applied to bacteria identification in blood, in: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2011. – volume: 34 start-page: 3043 year: 2008 end-page: 3054 ident: b0670 article-title: Predicting stock index increments by neural networks: the role of trading volume under different horizons publication-title: Expert Syst. Appl. – reference: M. Ranzato, A. Krizhevsky, G. Hinton, Factored 3-way restricted Boltzmann machines for modeling natural images, in: Proceedings of the International Conference on Artificial Intelligence and Statistics, 2010. – volume: 12 start-page: 401 year: 2004 end-page: 408 ident: b0160 article-title: Speech-to-text and speech-to-speech summarization of spontaneous speech publication-title: IEEE Trans. Speech Audio Process. – volume: 101 start-page: e215 year: 2000 end-page: e220 ident: b0195 article-title: PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals publication-title: Circulation – volume: 17 year: 2003 ident: b0420 article-title: The efficient market hypothesis and its critics publication-title: J. Econ. Perspect. – year: 1999 ident: b0165 article-title: Electronic Noses, Principles and Applications – reference: D. Lowe, Object recognition from local scale-invariant features, in: ICCV, 1999. – reference: R. Pascanu, T. Mikolov, Y. Bengio, Understanding the exploding gradient problem, Computing Research Repository (CoRR) abs/1211.5063, 2012. – volume: 101 start-page: 39 year: 2004 end-page: 46 ident: b0660 article-title: An electronic nose based on solid state sensor arrays for low-cost indoor air quality monitoring applications publication-title: Sens. Actuators B: Chem. – reference: M. Ranzato, G. Hinton, Modeling pixel means and covariances using factorized third-order Boltzmann machines, in: Proceedings of Computer Vision and Pattern Recognition Conference (CVPR 2010), 2010. – reference: transform toolbox for music processing, in: Seventh Sound and Music Computing Conference, 2010. – start-page: 15 year: 2002 end-page: 30 ident: b0130 article-title: Machine learning for sequential data: a review publication-title: Structural, Syntactic, and Statistical Pattern Recognition – volume: 174 start-page: 535 year: 2012 end-page: 546 ident: b0615 article-title: On time series features and kernels for machine olfaction publication-title: Sens. Actuators B: Chem. – volume: 50 start-page: 258 year: 2010 end-page: 269 ident: b0605 article-title: Combining multiple feature selection methods for stock prediction: union, intersection, and multi-intersection approaches publication-title: Decis. Support Syst. – volume: 7 start-page: 1231 year: 1996 end-page: 1249 ident: b0030 article-title: Input-output HMM’s for sequence processing publication-title: IEEE Trans. Neural Networks – volume: 70 start-page: 19 year: 2000 end-page: 24 ident: b0170 article-title: An electronic nose system to diagnose illness publication-title: Sens. Actuators B: Chem. – volume: 22 start-page: 56 year: 2010 ident: b0310 article-title: A survey on transfer learning publication-title: IEEE Trans. Knowl. Data Eng. – volume: vol. 7700 start-page: 599 year: 2010 end-page: 619 ident: b0255 article-title: A practical guide to training restricted boltzmann machines publication-title: Neural Networks: Tricks of the Trade – volume: 20 start-page: 30 year: 2012 end-page: 42 ident: b0110 article-title: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition publication-title: IEEE Transactions on Audio, Speech, and Language Processing – reference: C. Tucker, Self-organizing maps for time series analysis of electromyographic data, in: International Joint Conference on Neural Networks, 1999. IJCNN ’99, 1999, pp. 3577–3580. – reference: A. Saxe, P. Koh, Z. Chen, M. Bhand, B. Suresh, A.Y. Ng, On random weights and unsupervised feature learning, in: Proceedings of the 28th International Conference on Machine Learning, 2011. – reference: G. Taylor, G. Hinton, Factored conditional restricted Boltzmann machines for modeling motion style, in: Proceedings of the 26th International Conference on Machine Learning (ICML), 2009. – volume: 11 start-page: 2510 year: 2011 end-page: 2525 ident: b0275 article-title: Forecasting stock markets using wavelet transforms and recurrent neural networks: an integrated system based on artificial bee colony algorithm publication-title: Appl. Soft Comput. – volume: 50 start-page: 223 year: 2003 end-page: 235 ident: b0285 article-title: Recurrent neural networks for time series classification publication-title: Neurocomputing – volume: 36 start-page: 5932 year: 2009 end-page: 5941 ident: b0015 article-title: Surveying stock market forecasting techniques ĺc. Part ii: Soft computing methods publication-title: Expert Syst. Appl. – volume: 2 start-page: 189 year: 2002 end-page: 202 ident: b0220 article-title: Pattern analysis for machine olfaction: a review publication-title: IEEE Sens. J. – start-page: 1605 year: 2009 end-page: 1612 ident: b0325 article-title: Learning invariant features through topographic filter maps publication-title: IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009 – volume: vol. 01 start-page: 211 year: 2010 end-page: 214 ident: b0395 article-title: Applications of artificial neural networks in financial economics: a survey publication-title: Proceedings of the 2010 International Symposium on Computational Intelligence and Design – volume: 5 start-page: 157 year: 1994 end-page: 166 ident: b0045 article-title: Learning longterm dependencies with gradient descent is difficult publication-title: IEEE Trans. Neural Networks – volume: 15 start-page: 660 year: 2005 end-page: 666 ident: b0155 article-title: Motor primitives in vertebrates and invertebrates publication-title: Curr. Opin. Neurobiol. – volume: 19 start-page: 153 year: 2007 ident: b0035 article-title: Greedy layer-wise training of deep networks publication-title: Adv. Neural Inf. Process. Syst. – reference: Y. Bengio, Learning Deep Architectures for AI. Technical Report 1312. Dept. IRO, Universite de Montreal, 2007. – volume: 22 start-page: 1473 year: 2010 end-page: 1492 ident: b0445 article-title: Learning to represent spatial transformations with factored higher-order Boltzmann machines publication-title: Neural Comput. – volume: 37 start-page: 1466 year: 2001 end-page: 1467 ident: b0650 article-title: Classification of vintages of wine by artificial nose using time delay neural networks publication-title: Electron. Lett. – volume: 3 year: 2013 ident: b0630 article-title: Modeling physiological data with deep belief networks publication-title: Int. J. Inf. Educ. Technol. – volume: 10 start-page: 49 year: 2001 end-page: 61 ident: b0485 article-title: Feature-based classification of time-series data publication-title: Int. J. Comput. Res. – volume: 1 start-page: 4 year: 2002 ident: b0140 article-title: Bacteria classification using cyranose 320 electronic nose publication-title: Biomed. Eng. – volume: 49 start-page: 257 year: 2010 end-page: 271 ident: b0295 article-title: Independent component analysis of short-time Fourier transforms for spontaneous EEG/MEG analysis publication-title: NeuroImage – reference: H. Kamyshanska, R. Memisevic, On autoencoder scoring, in: Proceedings of the 30th International Conference on Machine Learning (ICML-13), JMLR Workshop and Conference Proceedings, 2013, pp. 720–728. – start-page: 183 year: 2000 end-page: 192 ident: b0080 article-title: Style machines publication-title: Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques – volume: 5 start-page: 49 year: 2003 end-page: 58 ident: b0180 article-title: A survey of kernels for structured data publication-title: SIGKDD Explor. Newslett. – year: 2007 ident: b0040 article-title: Scaling learning algorithms towards AI publication-title: Large-Scale Kernel Machines – volume: 20 start-page: 1631 year: 2008 end-page: 1649 ident: b0370 article-title: Representational power of restricted Boltzmann machines and deep belief networks publication-title: Neural Comput. – volume: 23 start-page: 469 year: 2010 end-page: 477 ident: b0115 article-title: Phone recognition with the mean-covariance restricted Boltzmann machine publication-title: Adv. Neural Inf. Process. Syst. – volume: 146 start-page: 297 year: 1999 end-page: 310 ident: b0235 article-title: Electronic noses: a review of signal processing techniques publication-title: IEE Proc. Circuits Devices Syst. – volume: 05 start-page: 597 year: 2006 end-page: 604 ident: b0655 article-title: 10 Challenging problems in data mining research publication-title: Int. J. Inf. Technol. Decis. Making – volume: 69 start-page: 336 year: 2000 end-page: 341 ident: b0175 article-title: An electronic nose system for monitoring the quality of potable water publication-title: Sens. Actuators B: Chem. – reference: H. Lee, R. Grosse, R. Ranganath, A.Y. Ng, Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations, in: 26th International Conference on Machine Learning, 2009. – volume: 124 start-page: 309 year: 2007 end-page: 316 ident: b0620 article-title: Gas concentration estimation in ternary mixtures with room temperature operating sensor array using tapped delay architectures publication-title: Sens. Actuators B: Chem. – volume: 13 start-page: 1578 year: 2013 end-page: 1592 ident: b0345 article-title: Fast classification of meat spoilage markers using nanostructured ZnO thin films and unsupervised feature learning publication-title: Sensors – reference: T. Duckett, M. Axelsson, A. Saffiotti, Learning to locate an odour source with a mobile robot, in: IEEE International Conference on Robotics and Automation, 2001. Proceedings 2001 ICRA, vol. 4, 2001, pp. 4017–4022. – reference: A. Mohamed, G. Hinton, Phone recognition using restricted Boltzmann machines, in: 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2010, pp. 4354–4357. – volume: vol. 7700 year: 2012 ident: b0430 article-title: Training deep and recurrent neural networks with hessian-free optimization publication-title: Neural Networks: Tricks of the Trade – volume: 41 start-page: 461 year: 2013 end-page: 481 ident: b0280 article-title: Feature learning and deep architectures: new directions for music informatics publication-title: J. Intell. Inf. Syst. – year: 1979 ident: b0410 article-title: Introduction to Dynamic Systems: Theory, Models, and Applications – volume: 131 start-page: 110 year: 2008 end-page: 116 ident: b0060 article-title: Preemptive identification of optimum fermentation time for black tea using electronic nose publication-title: Sens. Actuators B: Chem. – volume: 223 start-page: 96 year: 2006 end-page: 101 ident: b0085 article-title: Analysis of saffron volatile fraction by td–gc–ms and e-nose publication-title: Eur. Food Res. Technol. – reference: P. Hamel, D. Eck, Learning features from music audio with deep belief networks, in: 11th International Society for Music Information Retrieval Conference (ISMIR), 2010. – reference: E. Parris, M. Carey, Language independent gender identification, in: 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings, vol. 2, 1996, pp. 685–688. – reference: I. Sutskever, Training recurrent neural networks (Ph.D. thesis), University of Toronto, 2012. – reference: G. Taylor, G.E. Hinton, S. Roweis, Modeling human motion using binary latent variables, in: Advances in Neural Information Processing Systems, 2007. – volume: 4 year: 2011 ident: b0055 article-title: Mobile robots for localizing gas emission sources on landfill sites: is bio-inspiration the way to go? publication-title: Front. Neuroeng. – reference: W. Pan, L. Torresani, Unsupervised hierarchical modeling of locomotion styles, in: Proceedings of the 26th Annual International Conference on Machine Learning, 2009, pp. 785–792. – reference: D. Gruhl, R. Guha, R. Kumar, J. Novak, A. Tomkins, The predictive power of online chatter, in: Proceedings of the 11th ACM SIGKDD International Conference on Knowledge Discovery in Data Mining, 2005, pp. 78–87. – start-page: 5884 year: 2011 end-page: 5887 ident: b0305 article-title: Learning a better representation of speech soundwaves using restricted Boltzmann machines publication-title: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) – reference: M. Längkvist, A. Loutfi, Not all signals are created equal: dynamic objective auto-encoder for multivariate data, in: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2012. – start-page: 177 year: 2010 end-page: 187 ident: b0075 article-title: Large-scale machine learning with stochastic gradient descent publication-title: Proceedings of the 19th International Conference on Computational Statistics (COMPSTAT’2010) – volume: 14 start-page: 715 year: 2002 end-page: 770 ident: b0640 article-title: Slow feature analysis: unsupervised learning of invariances publication-title: Neural Comput. – reference: S. Dieleman, P. Brakel, B. Schrauwen, Audio-based music classification with a pretrained convolutional network, in: The International Society for Music Information Retrieval (ISMIR), 2011. – volume: 11 start-page: 625 year: 2010 end-page: 660 ident: b0145 article-title: Why does unsupervised pre-training help deep learning? publication-title: J. Mach. Learn. Res. – reference: D. Stavens, S. Thrun, Unsupervised learning of invariant features using video, in: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010, pp. 1649–1656. – reference: W.Y. Zou, A.Y. Ng, K. Yu, Unsupervised learning of visual invariance with temporal coherence, in: NIPS 2011 Workshop on Deep Learning and Unsupervised Feature Learning, 2011. – reference: G.E. Hinton, A. Krizhevsky, S.D. Wang, Transforming auto-encoders, in: Proceedings of the 21th International Conference on Artificial Neural Networks, vol. Part I, 2011, pp. 44–51. – volume: 8 start-page: 1741 year: 2011 end-page: 2552 ident: b0645 article-title: Modeling electroencephalography waveforms with semi-supervised deep belief nets: faster classification and anomaly measurement publication-title: J. Neural Eng. – volume: 3 start-page: 29 year: 1998 end-page: 48 ident: b0200 article-title: Practical parameterization of rotations using the exponential map publication-title: J. Graph. Tools – volume: 2 start-page: 1360 year: 2013 end-page: 1366 ident: b0005 article-title: State-of-the-art in stock prediction techniques publication-title: Int. J. Adv. Res. Electr. Electron. Instrum. Eng. – reference: Y. Bengio, A. Courville, P. Vincent, Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives. Technical Report, U. Montreal, 2012. Available from: – start-page: 83 year: 2011 end-page: 86 ident: b0010 article-title: Self-taught learning for activity spotting in on-body motion sensor data publication-title: ISWC 2011: Proceedings of the IEEE International Symposium on Wearable Computing – reference: Bo Chen, Jo-Anne Ting, B. Marlin, N. de Freitas, Deep learning of invariant spatio-temporal features from video, in: NIPS 2010 Deep Learning and Unsupervised Feature Learning Workshop, 2010. – reference: T. van Kasteren, A. Noulas, B. Kröse, Conditional random fields versus hidden markov models for activity recognition in temporal sensor data, in: Proceedings of the 14th Annual Conference of the Advanced School for Computing and Imaging (ASCI’08), The Netherlands, 2008. – year: 2006 ident: b0535 article-title: Efficient learning of sparse representations with an energy-based model publication-title: Advances in Neural Information Processing Systems (NIPS 2006) – reference: J.M. Wang, D.J. Fleet, A. Hertzmann, Multi-factor Gaussian process models for style-content separation, in: International Conference of Machine Learning (ICML), 2007, pp. 975–982. – reference: I. Sutskever, G. Hinton, Learning multilevel distributed representations for high-dimensional sequences, Technical Report, University of Toronto, 2006. – volume: 33 start-page: 51 year: 2000 end-page: 54 ident: b0190 article-title: Animation from observation: motion capture and motion editing publication-title: SIGGRAPH Comput. Graph. – reference: G.W. Taylor, Composable, distributed-state models for high-dimensional time series (Ph.D. thesis), Department of Computer Science, University of Toronto, 2009. – volume: 20 start-page: 1237 year: 2003 end-page: 1252 ident: b0290 article-title: Bubbles: a unifying framework for low-level statistical properties of natural image sequences publication-title: J. Opt. Soc. Am. A – reference: N. Dalal, B. Triggs, Histograms of oriented gradients for human detection, in: CVPR, 2005. – reference: K. Markov, T. Matsui, Music genre classification using self-taught learning via sparse coding, in: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012, pp. 1929–1932. – reference: K. Chang, J. Jang, C. Iliopoulos, Music genre classification via compressive sampling, in: Proceedings of the 11th International Conference on Music Information Retrieval (ISMIR), 2010, pp. 387–392. – start-page: 244 year: 2008 end-page: 249 ident: b0460 article-title: Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEG publication-title: IEEE Workshop on Machine Learning for Signal Processing, 2008. MLSP 2008 – volume: 313 start-page: 504 year: 2006 end-page: 507 ident: b0245 article-title: Reducing the dimensionality of data with neural networks publication-title: Science – volume: 20 start-page: 873 year: 2008 end-page: 880 ident: b0380 article-title: Sparse deep belief net model for visual area V2 publication-title: Adv. Neural Inf. Process. Syst. – reference: E. Keogh, S. Kasetty, On the need for time series data mining benchmarks: a survey and empirical demonstration, in: Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2002, pp. 102–111. – volume: vol. 39 year: 2009 ident: b0300 publication-title: Natural Image Statistics – reference: Q.V. Le, W.Y. Zou, S.Y. Yeung, A.Y. Ng, Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis, in: Computer Vision and Pattern Recognition (CVPR), 2011. – volume: 20 start-page: 14 year: 2012 end-page: 22 ident: b0465 article-title: Acoustic modeling using deep belief networks publication-title: IEEE Trans. Audio Speech Lang. Process. Arch. – reference: J. Nam, Learning feature representations for music classification (Ph.D. thesis), Stanford University, 2012. – start-page: 1 year: 2010 end-page: 9 ident: b0105 article-title: An analysis of single-layer networks in unsupervised feature learning publication-title: Engineering – reference: . – reference: S. Chiappa, J. Kober, J. Peters, Using Bayesian dynamical systems for motion template libraries, in: Advances in Neural Information Processing Systems, vol. 21, 2009, 297–304. – reference: M. Henaff, K. Jarrett, K. Kavukcuoglu, Y. LeCun, Unsupervised learning of sparse features for scalable audio classification, in: Proceedings of International Symposium on Music, Information Retrieval (ISMIR’11), 2011. – volume: 12 start-page: 2451 year: 2000 end-page: 2471 ident: b0185 article-title: Learning to forget: continual prediction with LSTM publication-title: Neural Comput. – volume: 20 start-page: 253 year: 1998 end-page: 263 ident: b0335 article-title: Time-delay recurrent neural network for temporal correlations and prediction publication-title: Neurocomputing – reference: R. Raina, A. Battle, H. Lee, B. Packer, A.Y. Ng, Self-taught learning: transfer learning from unlabeled data, in: Proceedings of the 24th International Conference on Machine Learning, 2007. – volume: 22 start-page: 1096 year: 2009 end-page: 1104 ident: b0390 article-title: Unsupervised feature learning for audio classification using convolutional deep belief networks publication-title: Adv. Neural Inf. Process. Syst. – start-page: 128 year: 2009 end-page: 143 ident: b0450 article-title: Dynamic factor graphs for time series modeling publication-title: Mach. Learn. Knowl. Discovery Databases – ident: 10.1016/j.patrec.2014.01.008_b0585 doi: 10.1145/1553374.1553505 – ident: 10.1016/j.patrec.2014.01.008_b0510 – ident: 10.1016/j.patrec.2014.01.008_b0500 doi: 10.1145/1553374.1553475 – ident: 10.1016/j.patrec.2014.01.008_b0090 – ident: 10.1016/j.patrec.2014.01.008_b0315 – volume: 13 start-page: 1578 issue: 2 year: 2013 ident: 10.1016/j.patrec.2014.01.008_b0345 article-title: Fast classification of meat spoilage markers using nanostructured ZnO thin films and unsupervised feature learning publication-title: Sensors doi: 10.3390/s130201578 – volume: 37 start-page: 328 year: 1989 ident: 10.1016/j.patrec.2014.01.008_b0625 article-title: Phoneme recognition using time-delay neural networks publication-title: IEEE Trans. Acoust. Speech Signal Process. doi: 10.1109/29.21701 – volume: 174 start-page: 535 year: 2012 ident: 10.1016/j.patrec.2014.01.008_b0615 article-title: On time series features and kernels for machine olfaction publication-title: Sens. Actuators B: Chem. doi: 10.1016/j.snb.2012.06.070 – volume: 22 start-page: 1096 year: 2009 ident: 10.1016/j.patrec.2014.01.008_b0390 article-title: Unsupervised feature learning for audio classification using convolutional deep belief networks publication-title: Adv. Neural Inf. Process. Syst. – ident: 10.1016/j.patrec.2014.01.008_b0330 doi: 10.1145/775047.775062 – year: 2005 ident: 10.1016/j.patrec.2014.01.008_b0415 – volume: 19 start-page: 153 year: 2007 ident: 10.1016/j.patrec.2014.01.008_b0035 article-title: Greedy layer-wise training of deep networks publication-title: Adv. Neural Inf. Process. Syst. – ident: 10.1016/j.patrec.2014.01.008_b0215 doi: 10.1145/1081870.1081883 – volume: 20 start-page: 1237 year: 2003 ident: 10.1016/j.patrec.2014.01.008_b0290 article-title: Bubbles: a unifying framework for low-level statistical properties of natural image sequences publication-title: J. Opt. Soc. Am. A doi: 10.1364/JOSAA.20.001237 – ident: 10.1016/j.patrec.2014.01.008_b0260 doi: 10.1007/978-3-642-21735-7_6 – volume: 36 start-page: 7313 year: 2009 ident: 10.1016/j.patrec.2014.01.008_b0400 article-title: Short-term stock price prediction based on echo state networks publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2008.09.049 – ident: 10.1016/j.patrec.2014.01.008_b0020 – start-page: 128 year: 2009 ident: 10.1016/j.patrec.2014.01.008_b0450 article-title: Dynamic factor graphs for time series modeling publication-title: Mach. Learn. Knowl. Discovery Databases doi: 10.1007/978-3-642-04174-7_9 – volume: 2 start-page: 189 issue: 3 year: 2002 ident: 10.1016/j.patrec.2014.01.008_b0220 article-title: Pattern analysis for machine olfaction: a review publication-title: IEEE Sens. J. doi: 10.1109/JSEN.2002.800688 – volume: 69 start-page: 336 year: 2000 ident: 10.1016/j.patrec.2014.01.008_b0175 article-title: An electronic nose system for monitoring the quality of potable water publication-title: Sens. Actuators B: Chem. doi: 10.1016/S0925-4005(00)00482-2 – volume: 17 year: 2003 ident: 10.1016/j.patrec.2014.01.008_b0420 article-title: The efficient market hypothesis and its critics publication-title: J. Econ. Perspect. doi: 10.1257/089533003321164958 – volume: 22 start-page: 56 year: 2010 ident: 10.1016/j.patrec.2014.01.008_b0310 article-title: A survey on transfer learning publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2009.191 – volume: 8 start-page: 1741 year: 2011 ident: 10.1016/j.patrec.2014.01.008_b0645 article-title: Modeling electroencephalography waveforms with semi-supervised deep belief nets: faster classification and anomaly measurement publication-title: J. Neural Eng. doi: 10.1088/1741-2560/8/3/036015 – ident: 10.1016/j.patrec.2014.01.008_b0355 – start-page: 1 year: 2007 ident: 10.1016/j.patrec.2014.01.008_b0440 article-title: Unsupervised learning of image transformations publication-title: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) – year: 2010 ident: 10.1016/j.patrec.2014.01.008_b0375 article-title: Convolutional networks and applications in vision – ident: 10.1016/j.patrec.2014.01.008_b0590 doi: 10.7551/mitpress/7503.003.0173 – year: 1999 ident: 10.1016/j.patrec.2014.01.008_b0165 – start-page: 83 year: 2011 ident: 10.1016/j.patrec.2014.01.008_b0010 article-title: Self-taught learning for activity spotting in on-body motion sensor data – volume: 14 start-page: 1771 year: 2002 ident: 10.1016/j.patrec.2014.01.008_b0250 article-title: Training products of experts by minimizing contrastive divergence publication-title: Neural Comput. doi: 10.1162/089976602760128018 – volume: 14 start-page: 715 year: 2002 ident: 10.1016/j.patrec.2014.01.008_b0640 article-title: Slow feature analysis: unsupervised learning of invariances publication-title: Neural Comput. doi: 10.1162/089976602317318938 – volume: vol. 7700 start-page: 599 year: 2010 ident: 10.1016/j.patrec.2014.01.008_b0255 article-title: A practical guide to training restricted boltzmann machines – volume: 131 start-page: 110 year: 2008 ident: 10.1016/j.patrec.2014.01.008_b0060 article-title: Preemptive identification of optimum fermentation time for black tea using electronic nose publication-title: Sens. Actuators B: Chem. doi: 10.1016/j.snb.2007.12.032 – volume: 5 start-page: 49 year: 2003 ident: 10.1016/j.patrec.2014.01.008_b0180 article-title: A survey of kernels for structured data publication-title: SIGKDD Explor. Newslett. doi: 10.1145/959242.959248 – volume: 20 start-page: 873 year: 2008 ident: 10.1016/j.patrec.2014.01.008_b0380 article-title: Sparse deep belief net model for visual area V2 publication-title: Adv. Neural Inf. Process. Syst. – ident: 10.1016/j.patrec.2014.01.008_b0470 doi: 10.1109/ICASSP.2010.5495651 – volume: 23 start-page: 469 year: 2010 ident: 10.1016/j.patrec.2014.01.008_b0115 article-title: Phone recognition with the mean-covariance restricted Boltzmann machine publication-title: Adv. Neural Inf. Process. Syst. – ident: 10.1016/j.patrec.2014.01.008_b0505 doi: 10.1109/ICASSP.1996.543213 – volume: 1 start-page: 34 year: 1965 ident: 10.1016/j.patrec.2014.01.008_b0150 article-title: The behavior of stock-market prices publication-title: J. Bus. doi: 10.1086/294743 – volume: 05 start-page: 597 year: 2006 ident: 10.1016/j.patrec.2014.01.008_b0655 article-title: 10 Challenging problems in data mining research publication-title: Int. J. Inf. Technol. Decis. Making doi: 10.1142/S0219622006002258 – volume: 2 start-page: 1 year: 2011 ident: 10.1016/j.patrec.2014.01.008_b0070 article-title: Twitter mood predicts the stock market publication-title: J. Comput. Sci. doi: 10.1016/j.jocs.2010.12.007 – volume: 3 start-page: 29 year: 1998 ident: 10.1016/j.patrec.2014.01.008_b0200 article-title: Practical parameterization of rotations using the exponential map publication-title: J. Graph. Tools doi: 10.1080/10867651.1998.10487493 – volume: 7 start-page: 1231 issue: 5 year: 1996 ident: 10.1016/j.patrec.2014.01.008_b0030 article-title: Input-output HMM’s for sequence processing publication-title: IEEE Trans. Neural Networks doi: 10.1109/72.536317 – volume: vol. 01 start-page: 211 year: 2010 ident: 10.1016/j.patrec.2014.01.008_b0395 article-title: Applications of artificial neural networks in financial economics: a survey – volume: 2 start-page: 1360 year: 2013 ident: 10.1016/j.patrec.2014.01.008_b0005 article-title: State-of-the-art in stock prediction techniques publication-title: Int. J. Adv. Res. Electr. Electron. Instrum. Eng. – volume: 15 start-page: 660 issue: 6 year: 2005 ident: 10.1016/j.patrec.2014.01.008_b0155 article-title: Motor primitives in vertebrates and invertebrates publication-title: Curr. Opin. Neurobiol. doi: 10.1016/j.conb.2005.10.011 – volume: 2012 year: 2012 ident: 10.1016/j.patrec.2014.01.008_b0350 article-title: Sleep stage classification using unsupervised feature learning publication-title: Adv. Artif. Neural Syst. – ident: 10.1016/j.patrec.2014.01.008_b0210 – volume: 18 start-page: 1527 year: 2006 ident: 10.1016/j.patrec.2014.01.008_b0265 article-title: A fast learning algorithm for deep belief nets publication-title: Neural Comput. doi: 10.1162/neco.2006.18.7.1527 – ident: 10.1016/j.patrec.2014.01.008_b0610 doi: 10.1109/IJCNN.1999.836246 – volume: 3 year: 2013 ident: 10.1016/j.patrec.2014.01.008_b0630 article-title: Modeling physiological data with deep belief networks publication-title: Int. J. Inf. Educ. Technol. – ident: 10.1016/j.patrec.2014.01.008_b0125 – volume: 12 start-page: 2451 year: 2000 ident: 10.1016/j.patrec.2014.01.008_b0185 article-title: Learning to forget: continual prediction with LSTM publication-title: Neural Comput. doi: 10.1162/089976600300015015 – volume: 33 start-page: 51 year: 2000 ident: 10.1016/j.patrec.2014.01.008_b0190 article-title: Animation from observation: motion capture and motion editing publication-title: SIGGRAPH Comput. Graph. doi: 10.1145/345370.345409 – ident: 10.1016/j.patrec.2014.01.008_b0560 doi: 10.1109/ISCAS.1991.176402 – ident: 10.1016/j.patrec.2014.01.008_b0635 doi: 10.1145/1273496.1273619 – volume: 29 start-page: 82 issue: 6 year: 2012 ident: 10.1016/j.patrec.2014.01.008_b0240 article-title: Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups publication-title: IEEE Signal Proc. Mag. doi: 10.1109/MSP.2012.2205597 – ident: 10.1016/j.patrec.2014.01.008_b0520 doi: 10.1145/1273496.1273592 – ident: 10.1016/j.patrec.2014.01.008_b0530 – year: 2005 ident: 10.1016/j.patrec.2014.01.008_b0550 article-title: Learning efficient auditory codes using spikes predicts cochlear filters – ident: 10.1016/j.patrec.2014.01.008_b0100 – start-page: 282 year: 2001 ident: 10.1016/j.patrec.2014.01.008_b0340 article-title: Conditional random fields: probabilistic models for segmenting and labeling sequence data – start-page: 183 year: 2000 ident: 10.1016/j.patrec.2014.01.008_b0080 article-title: Style machines – volume: 20 start-page: 14 issue: 1 year: 2012 ident: 10.1016/j.patrec.2014.01.008_b0465 article-title: Acoustic modeling using deep belief networks publication-title: IEEE Trans. Audio Speech Lang. Process. Arch. doi: 10.1109/TASL.2011.2109382 – ident: 10.1016/j.patrec.2014.01.008_b0230 – ident: 10.1016/j.patrec.2014.01.008_b0360 – volume: 41 start-page: 145 year: 2001 ident: 10.1016/j.patrec.2014.01.008_b0095 article-title: Independent component ordering in ica time series analysis publication-title: Neurocomputing doi: 10.1016/S0925-2312(00)00358-1 – ident: 10.1016/j.patrec.2014.01.008_b0490 – volume: 4 year: 2011 ident: 10.1016/j.patrec.2014.01.008_b0055 article-title: Mobile robots for localizing gas emission sources on landfill sites: is bio-inspiration the way to go? publication-title: Front. Neuroeng. – ident: 10.1016/j.patrec.2014.01.008_b0435 doi: 10.1007/978-3-642-21735-7_7 – volume: 20 start-page: 253 year: 1998 ident: 10.1016/j.patrec.2014.01.008_b0335 article-title: Time-delay recurrent neural network for temporal correlations and prediction publication-title: Neurocomputing doi: 10.1016/S0925-2312(98)00018-6 – volume: 146 start-page: 297 year: 1999 ident: 10.1016/j.patrec.2014.01.008_b0235 article-title: Electronic noses: a review of signal processing techniques publication-title: IEE Proc. Circuits Devices Syst. doi: 10.1049/ip-cds:19990670 – ident: 10.1016/j.patrec.2014.01.008_b0595 – year: 2007 ident: 10.1016/j.patrec.2014.01.008_b0040 article-title: Scaling learning algorithms towards AI – ident: 10.1016/j.patrec.2014.01.008_b0120 doi: 10.1109/CVPR.2005.177 – volume: 20 start-page: 1631 year: 2008 ident: 10.1016/j.patrec.2014.01.008_b0370 article-title: Representational power of restricted Boltzmann machines and deep belief networks publication-title: Neural Comput. doi: 10.1162/neco.2008.04-07-510 – ident: 10.1016/j.patrec.2014.01.008_b0065 – start-page: 5884 year: 2011 ident: 10.1016/j.patrec.2014.01.008_b0305 article-title: Learning a better representation of speech soundwaves using restricted Boltzmann machines – ident: 10.1016/j.patrec.2014.01.008_b0675 – volume: 11 start-page: 2510 year: 2011 ident: 10.1016/j.patrec.2014.01.008_b0275 article-title: Forecasting stock markets using wavelet transforms and recurrent neural networks: an integrated system based on artificial bee colony algorithm publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2010.09.007 – year: 1979 ident: 10.1016/j.patrec.2014.01.008_b0410 – ident: 10.1016/j.patrec.2014.01.008_b0365 doi: 10.1109/CVPR.2011.5995496 – volume: 313 start-page: 504 issue: 5786 year: 2006 ident: 10.1016/j.patrec.2014.01.008_b0245 article-title: Reducing the dimensionality of data with neural networks publication-title: Science doi: 10.1126/science.1127647 – ident: 10.1016/j.patrec.2014.01.008_b0385 doi: 10.1145/1553374.1553453 – volume: 36 start-page: 5932 year: 2009 ident: 10.1016/j.patrec.2014.01.008_b0015 article-title: Surveying stock market forecasting techniques ĺc. Part ii: Soft computing methods publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2008.07.006 – ident: 10.1016/j.patrec.2014.01.008_b0425 doi: 10.1109/ICASSP.2012.6288282 – ident: 10.1016/j.patrec.2014.01.008_b0555 doi: 10.1109/CVPR.2010.5539773 – ident: 10.1016/j.patrec.2014.01.008_b0225 – volume: vol. 7700 year: 2012 ident: 10.1016/j.patrec.2014.01.008_b0430 article-title: Training deep and recurrent neural networks with hessian-free optimization – start-page: 244 year: 2008 ident: 10.1016/j.patrec.2014.01.008_b0460 article-title: Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEG – ident: 10.1016/j.patrec.2014.01.008_b0570 – volume: 12 start-page: 401 year: 2004 ident: 10.1016/j.patrec.2014.01.008_b0160 article-title: Speech-to-text and speech-to-speech summarization of spontaneous speech publication-title: IEEE Trans. Speech Audio Process. doi: 10.1109/TSA.2004.828699 – volume: 57 start-page: 2884 year: 2010 ident: 10.1016/j.patrec.2014.01.008_b0600 article-title: Direct identification of bacteria in blood culture samples using an electronic nose publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2010.2049492 – ident: 10.1016/j.patrec.2014.01.008_b0475 – ident: 10.1016/j.patrec.2014.01.008_b0320 – volume: 50 start-page: 223 year: 2003 ident: 10.1016/j.patrec.2014.01.008_b0285 article-title: Recurrent neural networks for time series classification publication-title: Neurocomputing doi: 10.1016/S0925-2312(01)00706-8 – volume: 41 start-page: 461 issue: 3 year: 2013 ident: 10.1016/j.patrec.2014.01.008_b0280 article-title: Feature learning and deep architectures: new directions for music informatics publication-title: J. Intell. Inf. Syst. doi: 10.1007/s10844-013-0248-5 – volume: 101 start-page: 39 year: 2004 ident: 10.1016/j.patrec.2014.01.008_b0660 article-title: An electronic nose based on solid state sensor arrays for low-cost indoor air quality monitoring applications publication-title: Sens. Actuators B: Chem. doi: 10.1016/j.snb.2004.02.024 – ident: 10.1016/j.patrec.2014.01.008_b0025 – ident: 10.1016/j.patrec.2014.01.008_b0050 – ident: 10.1016/j.patrec.2014.01.008_b0580 doi: 10.1007/978-3-642-15567-3_11 – volume: 223 start-page: 96 year: 2006 ident: 10.1016/j.patrec.2014.01.008_b0085 article-title: Analysis of saffron volatile fraction by td–gc–ms and e-nose publication-title: Eur. Food Res. Technol. doi: 10.1007/s00217-005-0144-5 – year: 2003 ident: 10.1016/j.patrec.2014.01.008_b0495 article-title: Signal Conditioning and Preprocessing – ident: 10.1016/j.patrec.2014.01.008_b0480 – volume: 124 start-page: 309 year: 2007 ident: 10.1016/j.patrec.2014.01.008_b0620 article-title: Gas concentration estimation in ternary mixtures with room temperature operating sensor array using tapped delay architectures publication-title: Sens. Actuators B: Chem. doi: 10.1016/j.snb.2006.12.039 – volume: 10 start-page: 49 year: 2001 ident: 10.1016/j.patrec.2014.01.008_b0485 article-title: Feature-based classification of time-series data publication-title: Int. J. Comput. Res. – volume: 101 start-page: e215 year: 2000 ident: 10.1016/j.patrec.2014.01.008_b0195 article-title: PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals publication-title: Circulation doi: 10.1161/01.CIR.101.23.e215 – ident: 10.1016/j.patrec.2014.01.008_b0545 – start-page: 15 year: 2002 ident: 10.1016/j.patrec.2014.01.008_b0130 article-title: Machine learning for sequential data: a review – volume: 11 start-page: 625 year: 2010 ident: 10.1016/j.patrec.2014.01.008_b0145 article-title: Why does unsupervised pre-training help deep learning? publication-title: J. Mach. Learn. Res. – ident: 10.1016/j.patrec.2014.01.008_b0455 – year: 2006 ident: 10.1016/j.patrec.2014.01.008_b0535 article-title: Efficient learning of sparse representations with an energy-based model – volume: 34 start-page: 3043 year: 2008 ident: 10.1016/j.patrec.2014.01.008_b0670 article-title: Predicting stock index increments by neural networks: the role of trading volume under different horizons publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2007.06.023 – volume: 50 start-page: 258 year: 2010 ident: 10.1016/j.patrec.2014.01.008_b0605 article-title: Combining multiple feature selection methods for stock prediction: union, intersection, and multi-intersection approaches publication-title: Decis. Support Syst. doi: 10.1016/j.dss.2010.08.028 – ident: 10.1016/j.patrec.2014.01.008_b0405 doi: 10.1109/ICCV.1999.790410 – ident: 10.1016/j.patrec.2014.01.008_b0540 – volume: 9 start-page: 1735 year: 1997 ident: 10.1016/j.patrec.2014.01.008_b0270 article-title: Long short-term memory publication-title: Neural Comput. doi: 10.1162/neco.1997.9.8.1735 – volume: vol. 39 year: 2009 ident: 10.1016/j.patrec.2014.01.008_b0300 – volume: 20 start-page: 30 year: 2012 ident: 10.1016/j.patrec.2014.01.008_b0110 article-title: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition publication-title: IEEE Transactions on Audio, Speech, and Language Processing doi: 10.1109/TASL.2011.2134090 – start-page: 1 year: 2010 ident: 10.1016/j.patrec.2014.01.008_b0105 article-title: An analysis of single-layer networks in unsupervised feature learning publication-title: Engineering – start-page: 1605 year: 2009 ident: 10.1016/j.patrec.2014.01.008_b0325 article-title: Learning invariant features through topographic filter maps – start-page: 177 year: 2010 ident: 10.1016/j.patrec.2014.01.008_b0075 article-title: Large-scale machine learning with stochastic gradient descent – volume: 70 start-page: 19 year: 2000 ident: 10.1016/j.patrec.2014.01.008_b0170 article-title: An electronic nose system to diagnose illness publication-title: Sens. Actuators B: Chem. doi: 10.1016/S0925-4005(00)00548-7 – ident: 10.1016/j.patrec.2014.01.008_b0205 doi: 10.1109/ICASSP.2013.6638947 – volume: 5 start-page: 157 issue: 2 year: 1994 ident: 10.1016/j.patrec.2014.01.008_b0045 article-title: Learning longterm dependencies with gradient descent is difficult publication-title: IEEE Trans. Neural Networks doi: 10.1109/72.279181 – start-page: 1601 year: 2008 ident: 10.1016/j.patrec.2014.01.008_b0575 article-title: The recurrent temporal restricted Boltzmann machine publication-title: Adv. Neural Inf. Process. Syst. – volume: 3 start-page: 4 issue: 1 year: 1986 ident: 10.1016/j.patrec.2014.01.008_b0515 article-title: An introduction to hidden Markov models publication-title: IEEE ASSP Mag. doi: 10.1109/MASSP.1986.1165342 – ident: 10.1016/j.patrec.2014.01.008_b0525 doi: 10.1109/CVPR.2010.5539962 – volume: 1 start-page: 4 year: 2002 ident: 10.1016/j.patrec.2014.01.008_b0140 article-title: Bacteria classification using cyranose 320 electronic nose publication-title: Biomed. Eng. – volume: 49 start-page: 257 issue: 1 year: 2010 ident: 10.1016/j.patrec.2014.01.008_b0295 article-title: Independent component analysis of short-time Fourier transforms for spontaneous EEG/MEG analysis publication-title: NeuroImage doi: 10.1016/j.neuroimage.2009.08.028 – ident: 10.1016/j.patrec.2014.01.008_b0135 doi: 10.1109/ROBOT.2001.933245 – ident: 10.1016/j.patrec.2014.01.008_b0565 – volume: 22 start-page: 1473 year: 2010 ident: 10.1016/j.patrec.2014.01.008_b0445 article-title: Learning to represent spatial transformations with factored higher-order Boltzmann machines publication-title: Neural Comput. doi: 10.1162/neco.2010.01-09-953 – volume: 37 start-page: 1466 year: 2001 ident: 10.1016/j.patrec.2014.01.008_b0650 article-title: Classification of vintages of wine by artificial nose using time delay neural networks publication-title: Electron. Lett. doi: 10.1049/el:20010985 – volume: 96 start-page: 385 year: 2003 ident: 10.1016/j.patrec.2014.01.008_b0665 article-title: Improving pattern recognition of electronic nose data with time-delay neural networks publication-title: Sens. Actuators B: Chem. doi: 10.1016/S0925-4005(03)00574-4 |
| SSID | ssj0006398 |
| Score | 2.6376865 |
| Snippet | This paper gives a review of the recent developments in deep learning and unsupervised feature learning for time-series problems. While these techniques have... |
| SourceID | unpaywall swepub crossref elsevier |
| SourceType | Open Access Repository Enrichment Source Index Database Publisher |
| StartPage | 11 |
| SubjectTerms | Computer Science Datavetenskap Deep learning Time-series Unsupervised feature learning |
| SummonAdditionalLinks | – databaseName: Unpaywall dbid: UNPAY link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6V7QF6oFBALC_5AEevYmI7yUoIrYCq4lBx6EI5WbEzrgqrZLW7aVV-PeM4WSohVHrwIU5Gecw484018w3A6xwprrKZ5lKGrZsqFzxP0XEhK1t4whDKdlm-x_poLj-fqtMdGLo40ufrk9wp2GwWF_ieZt7RmNa2nq5x2qzaaXV-UfJUEhS-A7taEQYfwe78-Mvs-0DkHaotQ6SVZwQfUymHmrkusStsMmNgLxSyY-wMnSX_4ZMieege3G3rZXl1WS4W15zP4T58G0p4Ys7Jz0m7sRP3629Gx1u-1wO43-NRNosG9BB2sD6A_aHXA-uX_gHsXSMufAQnMxZrXljjWVuv22X45ayxYh47plDWd6M4Y2VdsQpx-WeGYDILLe15sH5cs64ZD514DPPDTycfjnjfn4E7gjkbjj6zRY7ekXITRZ6uVCLFnEI8mimtxTyxwhY2UKIpof1bn6NyThaiICFfpk9gVDc1PgWmlZMEHaz2mZJaOGtdpb1OnEq89MKOIR00ZFxPXh56aCzMkKX2w0S9mqBXkwhDeh0D30otI3nHDddng_JND0AisDDkX26QfBNtZXufQNv98fzrzDSrMxqt6RQ7hsnWlP7rkZ7dVuA53AtHMZvtBYw2qxZfEm7a2Ff9IvkNGEcaKA priority: 102 providerName: Unpaywall |
| Title | A review of unsupervised feature learning and deep learning for time-series modeling |
| URI | https://dx.doi.org/10.1016/j.patrec.2014.01.008 https://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-34597 http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-34597 |
| UnpaywallVersion | submittedVersion |
| Volume | 42 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Baden-Württemberg Complete Freedom Collection (Elsevier) customDbUrl: eissn: 1872-7344 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0006398 issn: 0167-8655 databaseCode: GBLVA dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVESC databaseName: Elsevier Freedom Collection customDbUrl: eissn: 1872-7344 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0006398 issn: 0167-8655 databaseCode: ACRLP dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals [SCFCJ] customDbUrl: eissn: 1872-7344 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0006398 issn: 0167-8655 databaseCode: AIKHN dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVESC databaseName: ScienceDirect (Elsevier) customDbUrl: eissn: 1872-7344 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0006398 issn: 0167-8655 databaseCode: .~1 dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVLSH databaseName: Elsevier Journals customDbUrl: mediaType: online eissn: 1872-7344 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0006398 issn: 0167-8655 databaseCode: AKRWK dateStart: 19821001 isFulltext: true providerName: Library Specific Holdings |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT9wwEB4hOBQOLQWqLgXkQ3sMGzd2HsdoAS0grSqVRXCyYsdGW62yEbtRxYXfzkweu3BAIA5RFMdWrBnHM2PNfB_Az9hiXKWj0BOCjm7ymHtxYI3HRa4Thz6E1HWW7ygcjsXFjbxZg0FXC0Nple3e3-zp9W7dtvRbafbLyaT_lxLoqawSQwSyRHUFu4iIxeD4cZXmgRY47vC9qXdXPlfneNF5syUgQy5q8E4imXzFPDU4olvwqSrK7OF_Np0-s0Nn2_C5dSBZ2szxK6zZYge-dOQMrP1Xd2DrGdLgLlylrClSYTPHqmJelbRHzG3OnK2hPVlLH3HHsiJnubXlqgX9WkYc9B4tVztnNXsOvtiD8dnp1WDotYQKnkG_ZOFZF-kkts6gNnyJpimTPLAxxmTYkmltY19znWjCMJM8dL9dbKUxIuEJDnJZ8A3Wi1lhvwMLpRFo63XoIilCbrQ2eehC30jfCcd1D4JOjsq0aONEejFVXVrZP9VIX5H0lc8VSr8H3nJU2aBtvNE_6lSkXqwahQbhjZG_Go0uv0M42yeT61TN7u_wqlQgMNjqwfFS4e-a0v6Hp_QDNumpyUM7gPXFfWUP0eNZ6KN6SR_BRnp-ORzhfTz6k94-AU6OA4Q |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT-MwEB4hOLAcgO2CKPvyYTmGxo2dx7FiF5XdwmUL4mbFjl0VVWnUNkJc-O07k0eBA2LFIRfHVqwZZ74Za-YbgB-xxbhKR6EnBF3dZDH34sAaj4tMJw59CKmrLN-rcHgtft_K2w04a2thKK2ysf21Ta-sdTPSa6TZK6bT3l9KoKeySgwRCIkwBNoSsh9RBHb6-JTngRActwTfNL2tn6uSvOjC2RKTIRcVeyd1mXwFn2oi0R3YLvMifbhPZ7NnQHS-D7uNB8kG9SY_wobNO7DXdmdgzc_agZ1nVIOfYDxgdZUKmztW5suyICOxtBlztuL2ZE3_iAlL84xl1hZPI-jYMmpC79F5tUtWtc_BFwdwff5rfDb0mo4KnkHHZOVZF-kkts6gOnyJ2JRKHtgYgzIcSbW2sa-5TjSRmEkeur6LrTRGJDzBRS4NDmEzn-f2CFgojUCw16GLpAi50dpkoQt9I30nHNddCFo5KtPQjVPXi5lq88ruVC19RdJXPlco_S5461VFTbfxxvyoVZF6cWwUIsIbK09qja6_Q0TbP6c3AzVfTPApVSAw2urC6Vrh_7Wl43dv6TtsD8eXIzW6uPrzGT7Qmzop7Qtsrhal_Yruz0p_q473Px-1A2k |
| linkToUnpaywall | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6V7QF6oFBALC_5AEevYmI7yUoIrYCq4lBx6EI5WbEzrgqrZLW7aVV-PeM4WSohVHrwIU5Gecw484018w3A6xwprrKZ5lKGrZsqFzxP0XEhK1t4whDKdlm-x_poLj-fqtMdGLo40ufrk9wp2GwWF_ieZt7RmNa2nq5x2qzaaXV-UfJUEhS-A7taEQYfwe78-Mvs-0DkHaotQ6SVZwQfUymHmrkusStsMmNgLxSyY-wMnSX_4ZMieege3G3rZXl1WS4W15zP4T58G0p4Ys7Jz0m7sRP3629Gx1u-1wO43-NRNosG9BB2sD6A_aHXA-uX_gHsXSMufAQnMxZrXljjWVuv22X45ayxYh47plDWd6M4Y2VdsQpx-WeGYDILLe15sH5cs64ZD514DPPDTycfjnjfn4E7gjkbjj6zRY7ekXITRZ6uVCLFnEI8mimtxTyxwhY2UKIpof1bn6NyThaiICFfpk9gVDc1PgWmlZMEHaz2mZJaOGtdpb1OnEq89MKOIR00ZFxPXh56aCzMkKX2w0S9mqBXkwhDeh0D30otI3nHDddng_JND0AisDDkX26QfBNtZXufQNv98fzrzDSrMxqt6RQ7hsnWlP7rkZ7dVuA53AtHMZvtBYw2qxZfEm7a2Ff9IvkNGEcaKA |
| 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+review+of+unsupervised+feature+learning+and+deep+learning+for+time-series+modeling&rft.jtitle=Pattern+recognition+letters&rft.au=L%C3%A4ngkvist%2C+Martin&rft.au=Karlsson%2C+Lars&rft.au=Loutfi%2C+Amy&rft.date=2014-06-01&rft.pub=Elsevier+B.V&rft.issn=0167-8655&rft.eissn=1872-7344&rft.volume=42&rft.spage=11&rft.epage=24&rft_id=info:doi/10.1016%2Fj.patrec.2014.01.008&rft.externalDocID=S0167865514000221 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-8655&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-8655&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-8655&client=summon |