End-to-End Deep Learning of Optical Fiber Communications

In this paper, we implement an optical fiber communication system as an end-to-end deep neural network, including the complete chain of transmitter, channel model, and receiver. This approach enables the optimization of the transceiver in a single end-to-end process. We illustrate the benefits of th...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Journal of lightwave technology Ročník 36; číslo 20; s. 4843 - 4855
Hlavní autoři:	Karanov, Boris, Chagnon, Mathieu, Thouin, Felix, Eriksson, Tobias A., Bulow, Henning, Lavery, Domanic, Bayvel, Polina, Schmalen, Laurent
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 15.10.2018 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Artificial neural networks Communication systems Communications systems Computer networks Computer simulation Deep learning detection Equalization Error correction Machine learning modulation neural networks Optical communication optical fiber communication Optical fibers Optical transmitters Optimization Pulse amplitude modulation Receivers Reconfiguration Training Transceivers Transmitters
ISSN:	0733-8724, 1558-2213
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	In this paper, we implement an optical fiber communication system as an end-to-end deep neural network, including the complete chain of transmitter, channel model, and receiver. This approach enables the optimization of the transceiver in a single end-to-end process. We illustrate the benefits of this method by applying it to intensity modulation/direct detection (IM/DD) systems and show that we can achieve bit error rates below the 6.7% hard-decision forward error correction (HD-FEC) threshold. We model all componentry of the transmitter and receiver, as well as the fiber channel, and apply deep learning to find transmitter and receiver configurations minimizing the symbol error rate. We propose and verify in simulations a training method that yields robust and flexible transceivers that allow-without reconfiguration-reliable transmission over a large range of link dispersions. The results from end-to-end deep learning are successfully verified for the first time in an experiment. In particular, we achieve information rates of 42 Gb/s below the HD-FEC threshold at distances beyond 40 km. We find that our results outperform conventional IM/DD solutions based on two- and four-level pulse amplitude modulation with feedforward equalization at the receiver. Our study is the first step toward end-to-end deep learning based optimization of optical fiber communication systems.
AbstractList	In this paper, we implement an optical fiber communication system as an end-to-end deep neural network, including the complete chain of transmitter, channel model, and receiver. This approach enables the optimization of the transceiver in a single end-to-end process. We illustrate the benefits of this method by applying it to intensity modulation/direct detection (IM/DD) systems and show that we can achieve bit error rates below the 6.7% hard-decision forward error correction (HD-FEC) threshold. We model all componentry of the transmitter and receiver, as well as the fiber channel, and apply deep learning to find transmitter and receiver configurations minimizing the symbol error rate. We propose and verify in simulations a training method that yields robust and flexible transceivers that allow-without reconfiguration-reliable transmission over a large range of link dispersions. The results from end-to-end deep learning are successfully verified for the first time in an experiment. In particular, we achieve information rates of 42 Gb/s below the HD-FEC threshold at distances beyond 40 km. We find that our results outperform conventional IM/DD solutions based on two- and four-level pulse amplitude modulation with feedforward equalization at the receiver. Our study is the first step toward end-to-end deep learning based optimization of optical fiber communication systems.
Author	Karanov, Boris Schmalen, Laurent Bulow, Henning Thouin, Felix Lavery, Domanic Chagnon, Mathieu Eriksson, Tobias A. Bayvel, Polina
Author_xml	– sequence: 1 givenname: Boris surname: Karanov fullname: Karanov, Boris email: boris.karanov.16@ucl.ac.uk organization: Nokia Bell Labs., Stuttgart, Germany – sequence: 2 givenname: Mathieu surname: Chagnon fullname: Chagnon, Mathieu organization: Nokia Bell Labs., Stuttgart, Germany – sequence: 3 givenname: Felix surname: Thouin fullname: Thouin, Felix organization: Sch. of Phys., Georgia Inst. of Technol., Atlanta, GA, USA – sequence: 4 givenname: Tobias A. surname: Eriksson fullname: Eriksson, Tobias A. organization: Quantum ICT Adv. Dev. Center, Nat. Inst. of Inf. & Commun. Technol., Tokyo, Japan – sequence: 5 givenname: Henning surname: Bulow fullname: Bulow, Henning organization: Nokia Bell Labs., Stuttgart, Germany – sequence: 6 givenname: Domanic surname: Lavery fullname: Lavery, Domanic organization: Dept. of Electron. & Electr. Eng., Univ. Coll. London, London, UK – sequence: 7 givenname: Polina surname: Bayvel fullname: Bayvel, Polina organization: Dept. of Electron. & Electr. Eng., Univ. Coll. London, London, UK – sequence: 8 givenname: Laurent surname: Schmalen fullname: Schmalen, Laurent organization: Nokia Bell Labs., Stuttgart, Germany
BookMark	eNp9kD1PwzAQhi1UJNrCjsQSiTnFH3Fsj6i0fChSlzJbTnJBrlo7OO7Av8clFQMD00mv3ufu9MzQxHkHCN0SvCAEq4e3arugmMgFlSVPwQWaEs5lTilhEzTFgrFcClpcodkw7DAmRSHFFMmVa_Po8zSyJ4A-q8AEZ91H5rts00fbmH22tjWEbOkPh6NLQbTeDdfosjP7AW7Oc47e16vt8iWvNs-vy8cqbxhjMe9qTCgnAEbwligQhGJgNW8UGAqloh1WLTG1EJ2oa1k3hKqGt0qlquGlYXN0P-7tg_88whD1zh-DSyc1pZxzgcuCp1Y5tprghyFApxsbfx6Nwdi9JlifLOlkSZ8s6bOlBOI_YB_swYSv_5C7EbEA8FuXBWNScfYN1mhy6Q
CODEN	JLTEDG
CitedBy_id	crossref_primary_10_1109_JLT_2019_2919713 crossref_primary_10_1109_JLT_2021_3138998 crossref_primary_10_1002_lpor_202400234 crossref_primary_10_1109_LPT_2019_2950189 crossref_primary_10_3390_app11041363 crossref_primary_10_3390_mi13010031 crossref_primary_10_1109_JLT_2021_3139167 crossref_primary_10_1109_JSAC_2020_3036950 crossref_primary_10_1088_1361_6463_abd4a6 crossref_primary_10_1117_1_OE_64_4_048103 crossref_primary_10_1109_JLT_2021_3086301 crossref_primary_10_1109_JLT_2023_3265308 crossref_primary_10_1364_PRJ_551798 crossref_primary_10_1109_JLT_2022_3216591 crossref_primary_10_1109_JLT_2024_3486561 crossref_primary_10_1109_JLT_2024_3521642 crossref_primary_10_1109_TWC_2020_2976004 crossref_primary_10_1109_TCOMM_2021_3114682 crossref_primary_10_3390_rs14184487 crossref_primary_10_1109_TCOMM_2022_3228648 crossref_primary_10_1088_1742_6596_2086_1_012163 crossref_primary_10_1109_JLT_2019_2897313 crossref_primary_10_1109_JLT_2024_3403129 crossref_primary_10_1364_JOCN_532742 crossref_primary_10_1109_JLT_2022_3213519 crossref_primary_10_1109_JLT_2023_3318295 crossref_primary_10_3390_photonics9010030 crossref_primary_10_1109_TCCN_2020_2985371 crossref_primary_10_1109_ACCESS_2019_2936796 crossref_primary_10_1088_2515_7647_ab437b crossref_primary_10_1364_JOCN_403500 crossref_primary_10_1109_JLT_2023_3276300 crossref_primary_10_1109_JLT_2023_3251660 crossref_primary_10_1109_JLT_2021_3133723 crossref_primary_10_1109_JSTQE_2022_3163474 crossref_primary_10_1364_JOCN_492770 crossref_primary_10_3390_electronics12204234 crossref_primary_10_1016_j_optlastec_2024_112090 crossref_primary_10_1364_AO_441357 crossref_primary_10_1002_lpor_202400097 crossref_primary_10_1109_ACCESS_2023_3245330 crossref_primary_10_1109_TCCN_2019_2943455 crossref_primary_10_1109_JPHOT_2023_3335398 crossref_primary_10_1364_JOCN_522761 crossref_primary_10_3390_photonics9080529 crossref_primary_10_3390_s23104618 crossref_primary_10_1109_ACCESS_2025_3569559 crossref_primary_10_1016_j_yofte_2025_104369 crossref_primary_10_1109_JLT_2023_3236400 crossref_primary_10_1109_JLT_2022_3149574 crossref_primary_10_1002_lpor_202100399 crossref_primary_10_1007_s11432_022_3643_y crossref_primary_10_1109_JSTQE_2022_3155990 crossref_primary_10_1364_OE_572940 crossref_primary_10_1109_LCOMM_2024_3387286 crossref_primary_10_1109_JPHOT_2020_3038534 crossref_primary_10_1109_JLT_2021_3117687 crossref_primary_10_1109_TWC_2021_3101364 crossref_primary_10_1109_JLT_2020_3031363 crossref_primary_10_1109_JLT_2022_3219639 crossref_primary_10_33317_ssurj_634 crossref_primary_10_1109_ACCESS_2025_3565502 crossref_primary_10_1109_TWC_2019_2950026 crossref_primary_10_1016_j_optlastec_2024_110935 crossref_primary_10_1109_JLT_2023_3282791 crossref_primary_10_3390_photonics12010039 crossref_primary_10_1088_1742_6596_1775_1_012005 crossref_primary_10_1070_QEL17656 crossref_primary_10_1364_JOCN_500500 crossref_primary_10_1038_s41467_024_50307_y crossref_primary_10_1109_TCOMM_2024_3454026 crossref_primary_10_1016_j_neucom_2022_09_088 crossref_primary_10_1007_s11082_025_08326_6 crossref_primary_10_1364_OE_563856 crossref_primary_10_1007_s00500_022_07181_x crossref_primary_10_1109_JLT_2023_3311716 crossref_primary_10_1016_j_iopt_2025_100009 crossref_primary_10_1109_JLT_2020_3015586 crossref_primary_10_1109_TCCN_2018_2881442 crossref_primary_10_3390_electronics11071138 crossref_primary_10_1109_JLT_2020_2983229 crossref_primary_10_1109_JLT_2025_3550277 crossref_primary_10_1109_TCOMM_2020_3025363 crossref_primary_10_1109_JPHOT_2021_3128420 crossref_primary_10_1364_PRJ_547255 crossref_primary_10_3390_photonics10030294 crossref_primary_10_1016_j_yofte_2024_104069 crossref_primary_10_1109_JLT_2022_3141222 crossref_primary_10_1109_JLT_2025_3528542 crossref_primary_10_1109_TCOMM_2020_3002915 crossref_primary_10_1016_j_phycom_2022_101903 crossref_primary_10_1002_adpr_202400123 crossref_primary_10_1109_ACCESS_2019_2903130 crossref_primary_10_1109_JLT_2020_2989210 crossref_primary_10_1109_JLT_2024_3487204 crossref_primary_10_1109_ACCESS_2021_3068162 crossref_primary_10_1007_s11801_025_4064_2 crossref_primary_10_1109_TCSII_2022_3152051 crossref_primary_10_1109_JLT_2020_2993271 crossref_primary_10_1109_JLT_2020_3034692 crossref_primary_10_1109_JLT_2025_3555756 crossref_primary_10_1109_JPHOT_2023_3277129 crossref_primary_10_1515_nanoph_2021_0578 crossref_primary_10_1109_JLT_2021_3057473 crossref_primary_10_1515_joc_2020_0270 crossref_primary_10_3103_S1068335622130103 crossref_primary_10_1007_s12596_022_00907_y crossref_primary_10_1109_LPT_2021_3067666 crossref_primary_10_1109_TCCN_2022_3161936 crossref_primary_10_1109_JLT_2023_3341495 crossref_primary_10_3103_S1068335624601602 crossref_primary_10_1016_j_infrared_2025_105724 crossref_primary_10_1109_JLT_2022_3148270 crossref_primary_10_1109_JPHOT_2023_3321736 crossref_primary_10_1109_JPHOT_2024_3370191 crossref_primary_10_1109_JLT_2024_3446573 crossref_primary_10_1109_JSEN_2022_3150240 crossref_primary_10_1109_JPHOT_2019_2938231 crossref_primary_10_1016_j_jneumeth_2021_109073 crossref_primary_10_1109_JLT_2021_3103339 crossref_primary_10_1109_JLT_2022_3169993 crossref_primary_10_1109_LCOMM_2020_3006921 crossref_primary_10_1109_JSTSP_2021_3098478 crossref_primary_10_1007_s11432_022_3734_0 crossref_primary_10_1109_TWC_2022_3157467 crossref_primary_10_1016_j_optcom_2023_129938 crossref_primary_10_3390_photonics10090993 crossref_primary_10_1016_j_exphem_2024_104166 crossref_primary_10_1109_JLT_2024_3454021 crossref_primary_10_1109_TCOMM_2019_2957482 crossref_primary_10_1109_TWC_2023_3241841 crossref_primary_10_1109_JLT_2019_2946572 crossref_primary_10_1109_JLT_2019_2922629 crossref_primary_10_1016_j_optlastec_2024_110729 crossref_primary_10_1088_2040_8986_ad261f crossref_primary_10_3390_photonics11080702 crossref_primary_10_1016_j_optlastec_2025_113358 crossref_primary_10_1016_j_yofte_2024_104047 crossref_primary_10_1007_s41683_022_00095_8 crossref_primary_10_1109_JLT_2020_2976479 crossref_primary_10_1109_JLT_2020_2991028 crossref_primary_10_1109_JLT_2021_3109852 crossref_primary_10_1109_JSTQE_2023_3309692 crossref_primary_10_3390_photonics11080781 crossref_primary_10_1016_j_photonics_2020_100787 crossref_primary_10_1103_PhysRevResearch_3_013200 crossref_primary_10_1016_j_neucom_2019_11_066 crossref_primary_10_1364_OL_553826 crossref_primary_10_1016_j_optlastec_2025_113597 crossref_primary_10_1109_JPHOT_2023_3344184 crossref_primary_10_3390_photonics11121178 crossref_primary_10_1109_TETCI_2022_3182765 crossref_primary_10_3390_telecom4040035 crossref_primary_10_3788_COL202422_040604 crossref_primary_10_4018_IJCINI_355767 crossref_primary_10_1109_JLT_2020_3007919 crossref_primary_10_1109_ACCESS_2019_2923321 crossref_primary_10_1109_TCOMM_2022_3213284 crossref_primary_10_1109_ACCESS_2019_2907752 crossref_primary_10_1016_j_camwa_2024_06_012 crossref_primary_10_3390_math13172792 crossref_primary_10_1109_TCOMM_2019_2951563 crossref_primary_10_1007_s11432_020_2873_x crossref_primary_10_1109_ACCESS_2021_3087136 crossref_primary_10_1016_j_yofte_2025_104218 crossref_primary_10_1109_JLT_2021_3139377 crossref_primary_10_1109_JLT_2020_2973232 crossref_primary_10_1109_JLT_2020_3033624 crossref_primary_10_1109_ACCESS_2020_2984218 crossref_primary_10_1109_JLT_2023_3282999 crossref_primary_10_1109_JLT_2024_3505415 crossref_primary_10_3390_photonics11100943 crossref_primary_10_1109_JLT_2023_3259929 crossref_primary_10_1109_JLT_2024_3466977 crossref_primary_10_3390_photonics11070613 crossref_primary_10_1038_s41598_025_07521_5 crossref_primary_10_1109_JLT_2024_3519360 crossref_primary_10_1109_JLT_2025_3591140 crossref_primary_10_1016_j_matpr_2022_07_183 crossref_primary_10_1109_JLT_2019_2901201 crossref_primary_10_1109_JLT_2023_3335394 crossref_primary_10_1007_s13369_025_10370_z crossref_primary_10_1016_j_optcom_2021_126843 crossref_primary_10_1007_s42484_024_00150_7 crossref_primary_10_1109_JLT_2020_3034047
Cites_doi	10.1109/LPT.2014.2375960 10.1038/323533a0 10.1109/JLT.2016.2590989 10.1109/JLT.2009.2039464 10.1109/TSMCC.2009.2038279 10.1002/9780470918524 10.1016/S0165-1684(00)00030-X 10.1109/JLT.2015.2508502 10.1109/LPT.2017.2755663 10.1109/MWC.2016.1500356WC 10.1016/0893-6080(89)90020-8 10.1109/JLT.2008.927791 10.1364/OL.40.005113 10.1109/JLT.2017.2729603 10.1109/JSTSP.2017.2784180 10.1109/TCCN.2017.2758370 10.1364/OE.20.012422
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SP 7U5 8FD H8D L7M
DOI	10.1109/JLT.2018.2865109
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Technology Research Database Aerospace Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Aerospace Database Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Aerospace Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Applied Sciences Physics
EISSN	1558-2213
EndPage	4855
ExternalDocumentID	10_1109_JLT_2018_2865109 8433895
Genre	orig-research
GrantInformation_xml	– fundername: German Academic Exchange Council – fundername: DAAD-RISE Professional scholarship – fundername: EU Marie Skłodowska-Curie project COIN grantid: 676448/H2020-MSCA-ITN-2015
GroupedDBID	-~X 0R~ 29K 4.4 5GY 6IK 85S 8SL 97E AAJGR AARMG AASAJ AAWJZ AAWTH ABAZT ABQJQ ABVLG ACBEA ACGFO ACGFS ACIWK AEDJG AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATHME ATWAV AYPRP AZSQR BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 D-I DSZJF DU5 EBS EJD ESBDL HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL OFLFD OPJBK P2P RIA RIE RNS ROL ROS TN5 TR6 ZCA AAYXX CITATION 7SP 7U5 8FD H8D L7M RIG
ID	FETCH-LOGICAL-c333t-fb01251eea75d19e7120e3b5c9ea2e692f09d1ab77f7bb8bc129c5d999e7a56a3
IEDL.DBID	RIE
ISICitedReferencesCount	293
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000444561700018&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0733-8724
IngestDate	Mon Jun 30 10:22:14 EDT 2025 Sat Nov 29 02:11:19 EST 2025 Tue Nov 18 22:07:53 EST 2025 Wed Aug 27 02:47:15 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	20
Language	English
License	https://creativecommons.org/licenses/by/3.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c333t-fb01251eea75d19e7120e3b5c9ea2e692f09d1ab77f7bb8bc129c5d999e7a56a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-5357-4292 0000-0002-1459-9128 0000-0002-8508-7234 0000-0003-2977-7713 0000-0002-8983-5818 0000-0003-4494-4786 0000-0003-1657-8109
OpenAccessLink	https://ieeexplore.ieee.org/document/8433895
PQID	2255570645
PQPubID	85485
PageCount	13
ParticipantIDs	proquest_journals_2255570645 crossref_citationtrail_10_1109_JLT_2018_2865109 ieee_primary_8433895 crossref_primary_10_1109_JLT_2018_2865109
PublicationCentury	2000
PublicationDate	2018-10-15
PublicationDateYYYYMMDD	2018-10-15
PublicationDate_xml	– month: 10 year: 2018 text: 2018-10-15 day: 15
PublicationDecade	2010
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	Journal of lightwave technology
PublicationTitleAbbrev	JLT
PublicationYear	2018
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	ref12 ref15 ref11 ref10 häger (ref14) 0 grassl (ref29) 2018 ref1 nair (ref21) 0 ref19 (ref24) 2018 ref18 rumelhart (ref22) 1986; 323 goodfellow (ref13) 2016 gaiarin (ref16) 0 estarán (ref17) 0 eiselt (ref20) 0 ref26 ref25 kingma (ref23) 2014 ref8 ref7 ref9 van der maaten (ref28) 2008; 9 ref4 ref3 ref6 ref5 pearson (ref27) 2011 khan (ref2) 0
References_xml	– ident: ref10 doi: 10.1109/LPT.2014.2375960 – volume: 323 start-page: 533 year: 1986 ident: ref22 article-title: Learning representations by back-propagating errors publication-title: Nature doi: 10.1038/323533a0 – ident: ref3 doi: 10.1109/JLT.2016.2590989 – ident: ref6 doi: 10.1109/JLT.2009.2039464 – year: 2018 ident: ref29 article-title: Bounds on the minimum distance of linear codes and quantum codes – ident: ref8 doi: 10.1109/TSMCC.2009.2038279 – ident: ref25 doi: 10.1002/9780470918524 – year: 2016 ident: ref13 publication-title: Deep Learning – ident: ref9 doi: 10.1016/S0165-1684(00)00030-X – ident: ref4 doi: 10.1109/JLT.2015.2508502 – start-page: 807 year: 0 ident: ref21 article-title: Rectified linear units improve restricted Boltzmann machines publication-title: Proc Int Conf Mach Learn – ident: ref12 doi: 10.1109/LPT.2017.2755663 – start-page: 106 year: 0 ident: ref17 article-title: Artificial neural networks for linear and non-linear impairment mitigation in high-baudrate IM/DD systems publication-title: Proc 42nd Eur Conf Opt Commun – ident: ref1 doi: 10.1109/MWC.2016.1500356WC – year: 2018 ident: ref24 – ident: ref7 doi: 10.1016/0893-6080(89)90020-8 – year: 0 ident: ref2 article-title: Machine learning methods for optical communication systems publication-title: Proc Adv Photon IPR NOMA Sensors Netw SPPCom PS OSA Tech Dig – year: 2011 ident: ref27 article-title: High-speed, analog-to-digital converter basics – year: 2014 ident: ref23 article-title: Adam: A method for stochastic optimization – ident: ref15 doi: 10.1109/JLT.2008.927791 – ident: ref11 doi: 10.1364/OL.40.005113 – year: 0 ident: ref14 article-title: Nonlinear interference mitigation via deep neural networks publication-title: Proc Tech Dig Opt Fiber Commun Conf – ident: ref26 doi: 10.1109/JLT.2017.2729603 – ident: ref19 doi: 10.1109/JSTSP.2017.2784180 – ident: ref18 doi: 10.1109/TCCN.2017.2758370 – ident: ref5 doi: 10.1364/OE.20.012422 – year: 0 ident: ref20 article-title: Direct detection solutions for 100G and beyond publication-title: Proc Opt Fiber Commun Conf – volume: 9 start-page: 2579 year: 2008 ident: ref28 article-title: Visualizing data using t-SNE publication-title: J Mach Learn Res – year: 0 ident: ref16 article-title: High speed PAM-8 optical interconnects with digital equalization based on neural network publication-title: Proc Asia Commun Photon Conf
SSID	ssj0014487
Score	2.686158
Snippet	In this paper, we implement an optical fiber communication system as an end-to-end deep neural network, including the complete chain of transmitter, channel...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	4843
SubjectTerms	Artificial neural networks Communication systems Communications systems Computer networks Computer simulation Deep learning detection Equalization Error correction Machine learning modulation neural networks Optical communication optical fiber communication Optical fibers Optical transmitters Optimization Pulse amplitude modulation Receivers Reconfiguration Training Transceivers Transmitters
Title	End-to-End Deep Learning of Optical Fiber Communications
URI	https://ieeexplore.ieee.org/document/8433895 https://www.proquest.com/docview/2255570645
Volume	36
WOSCitedRecordID	wos000444561700018&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: 1558-2213 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014487 issn: 0733-8724 databaseCode: RIE dateStart: 19830101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFH_MoeDF6aY4nZKDF8FuXbM0yVF0Q2RMDxN2K23yJoK0Y938-02yrCiK4Kk9JKX8Xl7e93sAV2GIkRBSWQpgYIdtBynGYcCUjhSLbCjOUXrMJxMxm8nnGtxUtTCI6JLPsGtfXSxfF2ptXWU9MTAGlWQ7sMM539RqVREDY2a40mhOqeHwaLANSYay9zie2hwu0bVVmC718IsIcjNVflzETrqMGv_7r0M48Fokud2Q_QhqmDeh4TVK4vm1bMKeS_BUZQvEMNfBqgjMg9wjLohvrPpKijl5WjiPNhnZ9BHyrWakPIaX0XB69xD4qQmBopSugnkWWqUFMeVM9yXyfhQizZiSmEYYy2geSt1PM87nPMtEpozEV0wbRRF5yuKUnkA9L3I8BUIpl7EWMrVOD-ZCgCrS2liAgmmjq7WhtwUyUb6luJ1s8Z440yKUiYE-sdAnHvo2XFc7Fpt2Gn-sbVmoq3Ue5TZ0trRKPL-VibmVbC-xeMDOft91Dvv221bq9FkH6qvlGi9gV32s3srlpTtKnwdlwqk
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB58ohfrE-szBy-Ca3eTzSY5irb4qNVDBW_LbjIVQdrSrf5-kzQtiiJ42j0k7PJNJvOeATiJY6RSKu0ogJEbth0VmMUR14ZqTl0ozlO6LTod-fysHufgbFYLg4g--QzP3auP5ZuBfneusoZMrUGl-Dws8jSlyaRaaxYzsIaGL44WjFkep-k0KBmrxm2767K45Lmrw_TJh1-EkJ-q8uMq9vKlVfvfn63DWtAjycWE8Bswh_1NqAWdkgSOrTZh2ad46moLZLNvovEgsg9yhTgkobXqCxn0yMPQ-7RJyyWQkG9VI9U2PLWa3cvrKMxNiDRjbBz1ytipLYiF4CZRKBIaIyu5VlhQzBTtxcokRSlET5SlLLWV-ZobqyqiKHhWsB1Y6A_6uAuEMaEyI1Xh3B7cBwE1NcbagJIbq63VoTEFMtehqbibbfGWe-MiVrmFPnfQ5wH6OpzOdgwnDTX-WLvloJ6tCyjX4WBKqzxwXJXbe8l1E8tSvvf7rmNYue7et_P2TeduH1bdd5wMSvgBLIxH73gIS_pj_FqNjvyx-gRVlMXw
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=End-to-End+Deep+Learning+of+Optical+Fiber+Communications&rft.jtitle=Journal+of+lightwave+technology&rft.au=Karanov%2C+Boris&rft.au=Chagnon%2C+Mathieu&rft.au=Thouin%2C+Felix&rft.au=Eriksson%2C+Tobias+A&rft.date=2018-10-15&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0733-8724&rft.eissn=1558-2213&rft.volume=36&rft.issue=20&rft.spage=4843&rft_id=info:doi/10.1109%2FJLT.2018.2865109&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0733-8724&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0733-8724&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0733-8724&client=summon