Learning to Detect

In this paper, we consider multiple-input-multiple-output detection using deep neural networks. We introduce two different deep architectures: a standard fully connected multi-layer network, and a detection network (DetNet), which is specifically designed for the task. The structure of DetNet is obt...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on signal processing Ročník 67; číslo 10; s. 2554 - 2564
Hlavní autoři:	Samuel, Neev, Diskin, Tzvi, Wiesel, Ami
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 15.05.2019 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithms Artificial neural networks Complexity theory Deep learning Detectors MIMO communication MIMO detection Multilayers Neural networks Signal processing algorithms
ISSN:	1053-587X, 1941-0476
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	In this paper, we consider multiple-input-multiple-output detection using deep neural networks. We introduce two different deep architectures: a standard fully connected multi-layer network, and a detection network (DetNet), which is specifically designed for the task. The structure of DetNet is obtained by unfolding the iterations of a projected gradient descent algorithm into a network. We compare the accuracy and runtime complexity of the proposed approaches and achieve state-of-the-art performance while maintaining low computational requirements. Furthermore, we manage to train a single network to detect over an entire distribution of channels. Finally, we consider detection with soft outputs and show that the networks can easily be modified to produce soft decisions.
AbstractList	In this paper, we consider multiple-input-multiple-output detection using deep neural networks. We introduce two different deep architectures: a standard fully connected multi-layer network, and a detection network (DetNet), which is specifically designed for the task. The structure of DetNet is obtained by unfolding the iterations of a projected gradient descent algorithm into a network. We compare the accuracy and runtime complexity of the proposed approaches and achieve state-of-the-art performance while maintaining low computational requirements. Furthermore, we manage to train a single network to detect over an entire distribution of channels. Finally, we consider detection with soft outputs and show that the networks can easily be modified to produce soft decisions.
Author	Samuel, Neev Diskin, Tzvi Wiesel, Ami
Author_xml	– sequence: 1 givenname: Neev surname: Samuel fullname: Samuel, Neev email: neev.samuel@mail.huji.ac.il organization: Sch. of Comput. Sci. & Eng., Hebrew Univ. of Jerusalem, Jerusalem, Israel – sequence: 2 givenname: Tzvi surname: Diskin fullname: Diskin, Tzvi email: zvidiskin@gmail.com organization: Sch. of Comput. Sci. & Eng., Hebrew Univ. of Jerusalem, Jerusalem, Israel – sequence: 3 givenname: Ami surname: Wiesel fullname: Wiesel, Ami email: amiw@cs.huji.ac.il organization: Sch. of Comput. Sci. & Eng., Hebrew Univ. of Jerusalem, Jerusalem, Israel
BookMark	eNp9jz1LA0EQhheJYBJtrASbgPWds3v7WUqMH3CgYAS7ZfeckwvxLu5uCv-9GxIsLGSKd4r3meGZkFE_9EjIBYWSUjDXy5fnkgE1JdPGaBBHZEwNpwVwJUd5B1EVQqu3EzKJcQVAOTdyTM5rdKHv-o9ZGma3mLBJp-S4deuIZ4eckte7xXL-UNRP94_zm7pomKGpUIJxJ7BqhfSCN1yCAiO0gTxcoZNeGqa8dxI9R-XeG_TKKQDHhVfeVVNytb-7CcPXFmOyq2Eb-vzSMkYBOKu0zi25bzVhiDFga5suudQNfQquW1sKdudvs7_d-duDfwbhD7gJ3acL3_8hl3ukQ8TfupY8C4vqB8G_ZRI
CODEN	ITPRED
CitedBy_id	crossref_primary_10_1109_ACCESS_2021_3121724 crossref_primary_10_1109_JSAC_2020_3036954 crossref_primary_10_1109_TVT_2024_3430353 crossref_primary_10_1109_ACCESS_2021_3073325 crossref_primary_10_1109_TWC_2020_2976004 crossref_primary_10_1016_j_sigpro_2024_109554 crossref_primary_10_1016_j_procs_2021_04_091 crossref_primary_10_3390_s25030669 crossref_primary_10_1109_TCCN_2022_3151935 crossref_primary_10_1109_TWC_2020_3032663 crossref_primary_10_1007_s11265_020_01631_1 crossref_primary_10_1109_TWC_2023_3261782 crossref_primary_10_1049_ell2_13155 crossref_primary_10_1109_TCOMM_2022_3186404 crossref_primary_10_1007_s11276_024_03788_0 crossref_primary_10_3390_signals1010005 crossref_primary_10_1088_2040_8986_ad08dc crossref_primary_10_3390_electronics14020335 crossref_primary_10_1109_TSUSC_2023_3324339 crossref_primary_10_1109_TIE_2023_3243301 crossref_primary_10_1109_TCOMM_2023_3237241 crossref_primary_10_1007_s11235_024_01231_5 crossref_primary_10_1109_LCOMM_2024_3451655 crossref_primary_10_1016_j_sigpro_2024_109543 crossref_primary_10_1109_TSP_2021_3076900 crossref_primary_10_1109_TVT_2023_3307449 crossref_primary_10_1109_TSP_2024_3359083 crossref_primary_10_1007_s11276_023_03545_9 crossref_primary_10_1109_TWC_2021_3054520 crossref_primary_10_1364_JOCN_492770 crossref_primary_10_1109_TWC_2020_2977340 crossref_primary_10_1109_LCOMM_2020_3011560 crossref_primary_10_1109_TCOMM_2023_3321735 crossref_primary_10_1016_j_dsp_2024_104627 crossref_primary_10_1109_TSP_2022_3180552 crossref_primary_10_1109_MWC_001_1900473 crossref_primary_10_1155_2022_8992478 crossref_primary_10_1002_inst_12416 crossref_primary_10_1109_TSP_2023_3310279 crossref_primary_10_1109_JPROC_2019_2957798 crossref_primary_10_1109_TCCN_2022_3168725 crossref_primary_10_1109_LWC_2024_3415175 crossref_primary_10_1109_TWC_2024_3514931 crossref_primary_10_1109_TCOMM_2022_3141399 crossref_primary_10_1109_ACCESS_2020_2978253 crossref_primary_10_1109_COMST_2021_3135542 crossref_primary_10_1109_LWC_2021_3111075 crossref_primary_10_1186_s13634_022_00885_0 crossref_primary_10_1109_TWC_2025_3541144 crossref_primary_10_1109_ACCESS_2023_3311821 crossref_primary_10_1109_ACCESS_2019_2937982 crossref_primary_10_1016_j_rineng_2025_105409 crossref_primary_10_1109_TCOMM_2023_3292468 crossref_primary_10_1109_TCOMM_2024_3454026 crossref_primary_10_1109_JIOT_2024_3368516 crossref_primary_10_1109_JSAC_2022_3180794 crossref_primary_10_1051_matecconf_202133604007 crossref_primary_10_1109_TSP_2022_3205478 crossref_primary_10_1007_s11425_023_2293_3 crossref_primary_10_1109_TCOMM_2023_3247733 crossref_primary_10_1016_j_indcrop_2023_116455 crossref_primary_10_1109_TSP_2020_3035832 crossref_primary_10_1186_s13677_020_00168_9 crossref_primary_10_1109_JSAC_2024_3443759 crossref_primary_10_1109_TWC_2019_2924220 crossref_primary_10_1109_TVT_2025_3534820 crossref_primary_10_1109_ACCESS_2020_3043004 crossref_primary_10_1109_TWC_2023_3292124 crossref_primary_10_1109_TCOMM_2022_3157314 crossref_primary_10_1109_TCOMM_2022_3218630 crossref_primary_10_1109_TWC_2023_3235059 crossref_primary_10_1109_JSAC_2025_3531558 crossref_primary_10_1049_cmu2_12424 crossref_primary_10_1109_TWC_2021_3100133 crossref_primary_10_1109_TWC_2024_3516738 crossref_primary_10_1049_cmu2_12669 crossref_primary_10_1109_TVT_2024_3360511 crossref_primary_10_1109_TWC_2022_3230662 crossref_primary_10_1109_TWC_2023_3272525 crossref_primary_10_1109_JPHOT_2019_2938231 crossref_primary_10_1016_j_phycom_2021_101343 crossref_primary_10_1109_TWC_2024_3422794 crossref_primary_10_1109_JPROC_2023_3247480 crossref_primary_10_1007_s11265_022_01827_7 crossref_primary_10_1109_TWC_2022_3157467 crossref_primary_10_1109_TMI_2019_2941271 crossref_primary_10_1109_TWC_2020_2981919 crossref_primary_10_1109_TVT_2024_3445912 crossref_primary_10_1109_TWC_2023_3241841 crossref_primary_10_1109_TWC_2023_3268945 crossref_primary_10_1109_ACCESS_2022_3206814 crossref_primary_10_1109_JSAC_2021_3087224 crossref_primary_10_1109_TWC_2022_3164203 crossref_primary_10_1109_TWC_2022_3181219 crossref_primary_10_1109_TVT_2022_3201961 crossref_primary_10_1109_TCOMM_2023_3294957 crossref_primary_10_1109_TWC_2020_3026471 crossref_primary_10_1016_j_aeue_2019_152964 crossref_primary_10_1109_TSP_2022_3143372 crossref_primary_10_1142_S0129065725500534 crossref_primary_10_1109_TWC_2020_3033334 crossref_primary_10_1109_TSP_2023_3284373 crossref_primary_10_1109_TWC_2021_3076527 crossref_primary_10_1109_LCOMM_2019_2950201 crossref_primary_10_1109_TCOMM_2022_3219141 crossref_primary_10_1109_TSP_2021_3117503 crossref_primary_10_1109_MWC_003_21003437 crossref_primary_10_1016_j_phycom_2024_102438 crossref_primary_10_1109_TCOMM_2023_3337272 crossref_primary_10_1109_COMST_2023_3300664 crossref_primary_10_1109_TSP_2023_3238275 crossref_primary_10_1016_j_aeue_2022_154350 crossref_primary_10_1109_ACCESS_2019_2928049 crossref_primary_10_1109_ACCESS_2020_2979156 crossref_primary_10_1109_TCOMM_2023_3299974 crossref_primary_10_3390_su16167039 crossref_primary_10_1109_ACCESS_2019_2927997 crossref_primary_10_1109_LCOMM_2020_2989672 crossref_primary_10_1109_TWC_2020_2996144 crossref_primary_10_1109_TCCN_2023_3235763 crossref_primary_10_1109_TWC_2025_3561242 crossref_primary_10_1109_ACCESS_2020_3006265 crossref_primary_10_1109_TCOMM_2023_3348839 crossref_primary_10_3390_app10134622 crossref_primary_10_1109_TVT_2022_3230143 crossref_primary_10_1109_LWC_2023_3234239 crossref_primary_10_1109_ACCESS_2021_3104660 crossref_primary_10_1109_ACCESS_2020_3044097 crossref_primary_10_1109_TWC_2020_3030882 crossref_primary_10_1109_TCOMM_2021_3114682 crossref_primary_10_1109_TWC_2024_3509713 crossref_primary_10_1109_LCOMM_2022_3197974 crossref_primary_10_1109_TWC_2021_3055202 crossref_primary_10_1109_ACCESS_2021_3125002 crossref_primary_10_1109_TSP_2023_3263255 crossref_primary_10_1109_TWC_2023_3336911 crossref_primary_10_1007_s00340_020_07571_9 crossref_primary_10_1016_j_phycom_2025_102637 crossref_primary_10_1109_ACCESS_2020_2985083 crossref_primary_10_1109_TWC_2022_3170510 crossref_primary_10_1109_JSAC_2021_3126087 crossref_primary_10_1109_TCCN_2020_2985371 crossref_primary_10_1109_ACCESS_2023_3310238 crossref_primary_10_1109_LWC_2023_3348933 crossref_primary_10_1109_TR_2022_3148114 crossref_primary_10_1109_TWC_2023_3330816 crossref_primary_10_1109_TVT_2022_3166399 crossref_primary_10_1109_TVT_2022_3226799 crossref_primary_10_1109_LCOMM_2020_3018260 crossref_primary_10_1109_MWC_013_2100652 crossref_primary_10_1016_j_aeue_2023_154712 crossref_primary_10_1109_JPROC_2024_3437730 crossref_primary_10_1109_TWC_2021_3123220 crossref_primary_10_1109_ACCESS_2022_3221800 crossref_primary_10_1109_TVT_2024_3392856 crossref_primary_10_1109_TWC_2022_3193885 crossref_primary_10_1109_ACCESS_2020_3035961 crossref_primary_10_1109_OJVT_2025_3574934 crossref_primary_10_1109_TSP_2023_3239170 crossref_primary_10_1109_ACCESS_2020_2987375 crossref_primary_10_1109_TCOMM_2019_2960361 crossref_primary_10_3390_rs12172729 crossref_primary_10_1016_j_dsp_2023_104027 crossref_primary_10_1109_TWC_2021_3082844 crossref_primary_10_1109_TWC_2023_3271521 crossref_primary_10_1016_j_phycom_2023_102189 crossref_primary_10_1109_JSAC_2021_3126080 crossref_primary_10_1109_LSP_2022_3179958 crossref_primary_10_1109_LCOMM_2020_3045665 crossref_primary_10_1109_TVT_2023_3325367 crossref_primary_10_1109_LWC_2020_3007198 crossref_primary_10_1016_j_compeleceng_2024_109608 crossref_primary_10_1109_TWC_2021_3068302 crossref_primary_10_1109_JIOT_2023_3274209 crossref_primary_10_1109_LCOMM_2022_3206414 crossref_primary_10_1109_TVT_2023_3241440 crossref_primary_10_1109_TCOMM_2021_3058999 crossref_primary_10_1109_TWC_2021_3051317 crossref_primary_10_1109_MSP_2023_3261505 crossref_primary_10_1038_s44172_023_00108_w crossref_primary_10_1109_TSP_2022_3229944 crossref_primary_10_1109_TWC_2022_3155945 crossref_primary_10_1109_TCOMM_2024_3394039 crossref_primary_10_1109_TVT_2021_3099640 crossref_primary_10_1109_TWC_2022_3227636 crossref_primary_10_1109_TCOMM_2022_3209888 crossref_primary_10_1109_TCCN_2023_3279260 crossref_primary_10_1109_TWC_2022_3190435 crossref_primary_10_33769_aupse_1140193 crossref_primary_10_1109_TAES_2024_3443020 crossref_primary_10_1109_TVT_2019_2922369 crossref_primary_10_1109_ACCESS_2024_3494752 crossref_primary_10_1109_JSAC_2021_3126064 crossref_primary_10_1109_TSP_2020_3048232 crossref_primary_10_1109_TCOMM_2023_3263874 crossref_primary_10_1109_TCOMM_2023_3292472 crossref_primary_10_3390_electronics13193945 crossref_primary_10_1109_LWC_2021_3106039 crossref_primary_10_1109_JSAC_2022_3191344 crossref_primary_10_1109_TSP_2023_3329964 crossref_primary_10_1109_ACCESS_2021_3069707 crossref_primary_10_1109_LWC_2023_3340172 crossref_primary_10_1109_JLT_2022_3148270 crossref_primary_10_1109_TMC_2024_3502574 crossref_primary_10_1109_TCCN_2024_3384500 crossref_primary_10_1109_TVT_2023_3269381 crossref_primary_10_1049_cmu2_12176 crossref_primary_10_1109_TVT_2021_3128693 crossref_primary_10_1109_TVLSI_2024_3392688 crossref_primary_10_1109_OJVT_2023_3334822 crossref_primary_10_1109_JETCAS_2020_3000103 crossref_primary_10_1016_j_aeue_2025_155815 crossref_primary_10_1109_TCOMM_2024_3516504 crossref_primary_10_1007_s11276_020_02412_1 crossref_primary_10_1109_TCOMM_2020_3007622 crossref_primary_10_1109_TSP_2023_3322852 crossref_primary_10_3390_telecom6030058 crossref_primary_10_1109_ACCESS_2020_3033989 crossref_primary_10_1109_ACCESS_2021_3065923 crossref_primary_10_1109_TWC_2023_3329521 crossref_primary_10_1109_ACCESS_2021_3087136 crossref_primary_10_1109_JSYST_2022_3191192 crossref_primary_10_1109_TVT_2022_3151246 crossref_primary_10_1109_TVT_2024_3391614 crossref_primary_10_1109_LCOMM_2020_3039528 crossref_primary_10_1109_LWC_2022_3147250
Cites_doi	10.1007/978-3-7908-2604-3_16 10.1038/nature16961 10.1109/TSP.2018.2868322 10.1109/JSTSP.2017.2788405 10.1109/TSP.2004.834267 10.1109/TIT.2014.2354403 10.1109/CVPR.2015.7298594 10.1109/TIT.2008.917634 10.1109/TIT.2002.800499 10.1109/JSAC.2005.862402 10.1109/CC.2017.8233654 10.1109/26.837052 10.1109/GlobalSIP.2016.7905837 10.1109/CAMSAP.2017.8313200 10.1109/ISIT.2015.7282651 10.1109/LWC.2017.2757490 10.1109/ICASSP.2017.7952561 10.1109/CISS.2017.7926071 10.1109/ALLERTON.2016.7852251 10.1109/JSTSP.2017.2784180 10.1109/MSP.2012.2205597 10.1109/MSP.2010.936019 10.1109/SPAWC.2017.8227772 10.1109/CVPR.2016.90 10.1109/TIT.2011.2143830 10.1109/TWC.2017.2654344 10.1038/nature14539
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TSP.2019.2899805
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1941-0476
EndPage	2564
ExternalDocumentID	10_1109_TSP_2019_2899805 8642915
Genre	orig-research
GrantInformation_xml	– fundername: Iowa Science Foundation grantid: 1339/15 funderid: 10.13039/100012579 – fundername: Heron Consortium
GroupedDBID	-~X .DC 0R~ 29I 4.4 5GY 6IK 85S 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK ACNCT AENEX AGQYO AHBIQ AJQPL AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 EBS EJD F5P HZ~ IFIPE IPLJI JAVBF LAI MS~ O9- OCL P2P RIA RIE RNS TAE TN5 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D RIG
ID	FETCH-LOGICAL-c291t-7524a5e3f56b54c460709589090947ea6b6927bba6eb4e7adceb7a700a45b7ba3
IEDL.DBID	RIE
ISICitedReferencesCount	356
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000464941100004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1053-587X
IngestDate	Mon Jun 30 10:14:35 EDT 2025 Sat Nov 29 04:10:48 EST 2025 Tue Nov 18 22:27:42 EST 2025 Wed Aug 27 02:47:12 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	10
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c291t-7524a5e3f56b54c460709589090947ea6b6927bba6eb4e7adceb7a700a45b7ba3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-2296-6952 0000-0003-4284-102X
PQID	2210042388
PQPubID	85478
PageCount	11
ParticipantIDs	crossref_citationtrail_10_1109_TSP_2019_2899805 proquest_journals_2210042388 ieee_primary_8642915 crossref_primary_10_1109_TSP_2019_2899805
PublicationCentury	2000
PublicationDate	2019-05-15
PublicationDateYYYYMMDD	2019-05-15
PublicationDate_xml	– month: 05 year: 2019 text: 2019-05-15 day: 15
PublicationDecade	2010
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on signal processing
PublicationTitleAbbrev	TSP
PublicationYear	2019
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref34 ref12 ref37 hershey (ref14) 2014 ref31 ref30 ref11 verdu (ref1) 1998 gregor (ref15) 0 ref2 ref39 ref17 ref38 ref16 ref19 farsad (ref22) 2017 abadi (ref36) 2016 o'shea (ref27) 2017 o'shea (ref25) 0 silver (ref13) 2016; 529 ref24 ref23 ref26 rumelhart (ref33) 1988; 5 kingma (ref35) 2014 graves (ref10) 0 ref21 glorot (ref32) 0; 9 ref28 lecun (ref8) 2015; 521 nachmani (ref18) 2017 ref29 o'shea (ref20) 2017 ref7 ref9 ref4 ref3 ref6 ref5 ref40 bailey (ref41) 1995; 156
References_xml	– ident: ref34 doi: 10.1007/978-3-7908-2604-3_16 – volume: 529 start-page: 484 year: 2016 ident: ref13 article-title: Mastering the game of go with deep neural networks and tree search publication-title: Nature doi: 10.1038/nature16961 – ident: ref23 doi: 10.1109/TSP.2018.2868322 – ident: ref19 doi: 10.1109/JSTSP.2017.2788405 – year: 2016 ident: ref36 article-title: Tensorflow: Large-scale machine learning on heterogeneous distributed systems – ident: ref37 doi: 10.1109/TSP.2004.834267 – ident: ref40 doi: 10.1109/TIT.2014.2354403 – ident: ref12 doi: 10.1109/CVPR.2015.7298594 – year: 1998 ident: ref1 publication-title: Multiuser Detection – ident: ref7 doi: 10.1109/TIT.2008.917634 – year: 2017 ident: ref27 article-title: Deep learning based MIMO communications – year: 2014 ident: ref35 article-title: Adam: A method for stochastic optimization – ident: ref2 doi: 10.1109/TIT.2002.800499 – ident: ref3 doi: 10.1109/JSAC.2005.862402 – ident: ref29 doi: 10.1109/CC.2017.8233654 – ident: ref39 doi: 10.1109/26.837052 – year: 2014 ident: ref14 article-title: Deep unfolding: Model-based inspiration of novel deep architectures – ident: ref16 doi: 10.1109/GlobalSIP.2016.7905837 – ident: ref30 doi: 10.1109/CAMSAP.2017.8313200 – ident: ref5 doi: 10.1109/ISIT.2015.7282651 – ident: ref24 doi: 10.1109/LWC.2017.2757490 – volume: 156 year: 1995 ident: ref41 publication-title: The NAS Parallel Benchmarks 2 0 – year: 2017 ident: ref22 article-title: Detection algorithms for communication systems using deep learning – ident: ref31 doi: 10.1109/ICASSP.2017.7952561 – year: 2017 ident: ref18 article-title: RNN decoding of linear block codes – ident: ref21 doi: 10.1109/CISS.2017.7926071 – volume: 9 start-page: 249 year: 0 ident: ref32 article-title: Understanding the difficulty of training deep feedforward neural networks publication-title: Proc 13th Int Conf Artif Intell Statist – ident: ref17 doi: 10.1109/ALLERTON.2016.7852251 – ident: ref26 doi: 10.1109/JSTSP.2017.2784180 – volume: 5 year: 1988 ident: ref33 article-title: Learning representations by back-propagating errors publication-title: Cogn Model – year: 2017 ident: ref20 article-title: An introduction to machine learning communications systems – ident: ref9 doi: 10.1109/MSP.2012.2205597 – start-page: 1764 year: 0 ident: ref10 article-title: Towards end-to-end speech recognition with recurrent neural networks publication-title: Proc Int Conf Mach Learn – ident: ref6 doi: 10.1109/MSP.2010.936019 – ident: ref28 doi: 10.1109/SPAWC.2017.8227772 – ident: ref11 doi: 10.1109/CVPR.2016.90 – start-page: 1 year: 0 ident: ref25 article-title: Learning approximate neural estimators for wireless channel state information publication-title: Proc IEEE 27th Int Workshop Machine Learn Signal Process – ident: ref38 doi: 10.1109/TIT.2011.2143830 – ident: ref4 doi: 10.1109/TWC.2017.2654344 – start-page: 399 year: 0 ident: ref15 article-title: Learning fast approximations of sparse coding publication-title: Proc 27th Int Conf Mach Learn – volume: 521 start-page: 436 year: 2015 ident: ref8 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539
SSID	ssj0014496
Score	2.6890635
Snippet	In this paper, we consider multiple-input-multiple-output detection using deep neural networks. We introduce two different deep architectures: a standard fully...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	2554
SubjectTerms	Algorithms Artificial neural networks Complexity theory Deep learning Detectors MIMO communication MIMO detection Multilayers Neural networks Signal processing algorithms
Title	Learning to Detect
URI	https://ieeexplore.ieee.org/document/8642915 https://www.proquest.com/docview/2210042388
Volume	67
WOSCitedRecordID	wos000464941100004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1941-0476 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014496 issn: 1053-587X databaseCode: RIE dateStart: 19910101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB5q8aAHtVaxWiUHL4Jp0-z7KGrxIKVghd7C7mYigrTSpv5-d7dpKCiC5LKH3U34spOZyTw-gGumpCnkgMRMI4mdSa1jpwRp7CwTpXNDikIH1pJnMRrJ6VSNG3Bb18IgYkg-w54fhlh-Prcr_6usL52xrHxF-Y4QfF2rVUcMKA1cXM5ccPeVYroJSSaqP3kZ-xwu1QvOhSeq21JBgVPlx4c4aJfh4f-e6wgOKisyulu_9hY0cHYM-1u9BdvQqjqnvkXlPHpAHys4gdfh4-T-Ka4IEGLr9itjwVKqGZKCccOopdzJp2JSJe6iAjU3XKXCGM3RUBQ6t2iEFkmiKTPCaHIKzdl8hmcQCYI5zwlFzq3vEagTlnO0TiSdBygL1YH-BpPMVt3BPUnFRxa8hERlDsXMo5hVKHbgpl7xue6M8cfctketnlcB1oHuBvasEp1llqaDkKwj5fnvqy5gz-_tQ_gD1oVmuVjhJezar_J9ubgKp-IbRnCxdw
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB5KFdSDWqtYnz14EUybJvs8iloq1lKwQm9hdzMRQVppU3-_u9s0FBRBcslhH-HLTmYm8_gArqgUOhOdOKAK48Ca1CqwSpAE1jKRKtVxlinPWtLng4EYj-WwAjdlLQwi-uQzbLlbH8tPp2bhfpW1hTWWpaso36CEROGyWquMGRDi2biswWB3Fny8CkqGsj16GbosLtny7oWjqltTQp5V5cen2OuX7t7_nmwfdgs7snm7fPE1qODkAHbWugvWoVb0Tn1r5tPmPbpowSG8dh9Gd72goEAIjF0vDziNiKIYZ5RpSgxhVkIlFTK0F-GomGYy4lorhpogV6lBzRUPQ0Wo5lrFR1CdTCd4DE0eY8rSmCBjxnUJVCFNGRorlNYHFJlsQHuFSWKK_uCOpuIj8X5CKBOLYuJQTAoUG3Bdzvhc9sb4Y2zdoVaOKwBrwNkK9qQQnnkSRR2friPEye-zLmGrN3ruJ_3HwdMpbLt9XEC_Q8-gms8WeA6b5it_n88u_An5BrQPtL4
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=Learning+to+Detect&rft.jtitle=IEEE+transactions+on+signal+processing&rft.au=Neev+Samuel&rft.au=Diskin%2C+Tzvi&rft.au=Wiesel%2C+Ami&rft.date=2019-05-15&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1053-587X&rft.eissn=1941-0476&rft.volume=67&rft.issue=10&rft.spage=2554&rft_id=info:doi/10.1109%2FTSP.2019.2899805&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1053-587X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1053-587X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1053-587X&client=summon