Robust inverse-design of scattering spectrum in core-shell structure using modified denoising autoencoder neural network
Neural network-based inverse design of nanophotonic device network is computationally and time efficient, but in general suffers the problems of robustness and stability against variation of the input target electromagnetic response. The inverse design network is required to be robust against the in...
Uložené v:
| Vydané v: | Optics express Ročník 27; číslo 25; s. 36276 |
|---|---|
| Hlavní autori: | , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
United States
09.12.2019
|
| ISSN: | 1094-4087, 1094-4087 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Neural network-based inverse design of nanophotonic device network is computationally and time efficient, but in general suffers the problems of robustness and stability against variation of the input target electromagnetic response. The inverse design network is required to be robust against the input electromagnetic response and to be capable of approximating the given electromagnetic response, even under the circumstances that the exact target response may not exist. We introduce a modified denoising autoencoder network to ensure the robustness of neural network-based inverse design, which consists of (1) a pre-trained network as a substitute of numerical simulation and (2) an inverse design network. We further purposely train the network with certain random disturbances added to the training dataset generated by the pre-trained network. Consequently, our modified denoising autoencoder network is more robust and more accurate than the conventional fully connected neural network. The strength and flexibility of our proposed network is illustrated via three concrete examples of achieving the desired scattering spectra of layered spherical scatterers. |
|---|---|
| AbstractList | Neural network-based inverse design of nanophotonic device network is computationally and time efficient, but in general suffers the problems of robustness and stability against variation of the input target electromagnetic response. The inverse design network is required to be robust against the input electromagnetic response and to be capable of approximating the given electromagnetic response, even under the circumstances that the exact target response may not exist. We introduce a modified denoising autoencoder network to ensure the robustness of neural network-based inverse design, which consists of (1) a pre-trained network as a substitute of numerical simulation and (2) an inverse design network. We further purposely train the network with certain random disturbances added to the training dataset generated by the pre-trained network. Consequently, our modified denoising autoencoder network is more robust and more accurate than the conventional fully connected neural network. The strength and flexibility of our proposed network is illustrated via three concrete examples of achieving the desired scattering spectra of layered spherical scatterers.Neural network-based inverse design of nanophotonic device network is computationally and time efficient, but in general suffers the problems of robustness and stability against variation of the input target electromagnetic response. The inverse design network is required to be robust against the input electromagnetic response and to be capable of approximating the given electromagnetic response, even under the circumstances that the exact target response may not exist. We introduce a modified denoising autoencoder network to ensure the robustness of neural network-based inverse design, which consists of (1) a pre-trained network as a substitute of numerical simulation and (2) an inverse design network. We further purposely train the network with certain random disturbances added to the training dataset generated by the pre-trained network. Consequently, our modified denoising autoencoder network is more robust and more accurate than the conventional fully connected neural network. The strength and flexibility of our proposed network is illustrated via three concrete examples of achieving the desired scattering spectra of layered spherical scatterers. Neural network-based inverse design of nanophotonic device network is computationally and time efficient, but in general suffers the problems of robustness and stability against variation of the input target electromagnetic response. The inverse design network is required to be robust against the input electromagnetic response and to be capable of approximating the given electromagnetic response, even under the circumstances that the exact target response may not exist. We introduce a modified denoising autoencoder network to ensure the robustness of neural network-based inverse design, which consists of (1) a pre-trained network as a substitute of numerical simulation and (2) an inverse design network. We further purposely train the network with certain random disturbances added to the training dataset generated by the pre-trained network. Consequently, our modified denoising autoencoder network is more robust and more accurate than the conventional fully connected neural network. The strength and flexibility of our proposed network is illustrated via three concrete examples of achieving the desired scattering spectra of layered spherical scatterers. |
| Author | Hu, Baiqiang Xu, Jing Wu, Bei Tan, Dong Chen, Yuntian |
| Author_xml | – sequence: 1 givenname: Baiqiang surname: Hu fullname: Hu, Baiqiang – sequence: 2 givenname: Bei surname: Wu fullname: Wu, Bei – sequence: 3 givenname: Dong surname: Tan fullname: Tan, Dong – sequence: 4 givenname: Jing surname: Xu fullname: Xu, Jing – sequence: 5 givenname: Yuntian surname: Chen fullname: Chen, Yuntian |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/31873410$$D View this record in MEDLINE/PubMed |
| BookMark | eNptkctrFTEUxoO02Jc715KlC-eax0wyWUq5WqFwQdp1yCQnNTqTXPOo-t877W1BxNV3-PidB-c7Q0cxRUDoNSUbykX_frfdMLkhXDApXqBTSlTf9WSUR3_VJ-islG-E0F4q-RKdcDpK3lNyin59SVMrFYd4D7lA56CEu4iTx8WaWiGHeIfLHmzNbVkpbFOGrnyFecZl9WxtGXArD9iSXPABHHYQU3i0TKsJok0OMo7QsplXqT9T_n6Bjr2ZC7x60nN0-3F7c3nVXe8-fb78cN1ZzlTtBhiJ8EQNUgkhfT_5UanBT4yq0XM3eGGks1ZMTNCRud6NgwSiJmrVMFkv-Dl6e5i7z-lHg1L1EopdzzcRUiuacU7WTXygK_rmCW3TAk7vc1hM_q2fv7UC7ADYnErJ4LUN1dSQYs0mzJoS_RCJ3m01k_oQydr07p-m57n_xf8AQGeOpA |
| CitedBy_id | crossref_primary_10_1016_j_photonics_2022_101066 crossref_primary_10_29026_oea_2022_210147 crossref_primary_10_1002_idm2_12049 crossref_primary_10_1364_PRJ_415960 crossref_primary_10_1016_j_ijmecsci_2025_110335 crossref_primary_10_3390_nano11030633 crossref_primary_10_1002_lpor_202300855 crossref_primary_10_1515_nanoph_2022_0537 crossref_primary_10_1109_JLT_2022_3185059 crossref_primary_10_1515_nanoph_2020_0240 crossref_primary_10_1088_2515_7647_acc7e5 crossref_primary_10_1016_j_cossms_2024_101144 |
| Cites_doi | 10.1038/s41598-017-01939-2 10.1021/acsami.9b05857 10.1063/1.5033327 10.1103/PhysRevLett.100.153904 10.1038/s41566-018-0246-9 10.1364/OME.9.001842 10.1109/TAP.2007.891552 10.1021/acs.nanolett.8b03171 10.1021/acsphotonics.7b01377 10.1364/OE.22.016178 10.1364/OE.26.032704 10.1364/OE.27.016047 10.1103/PhysRevLett.122.234502 10.1364/OE.25.021358 10.1126/science.220.4598.671 10.1038/s41598-018-37952-2 10.1364/OME.9.000469 10.1364/JOSAB.28.000387 10.1364/OE.26.014678 10.1126/sciadv.aar4206 10.1364/OE.26.024135 10.1021/acsphotonics.5b00463 10.1021/acsnano.8b03569 10.1364/OE.26.033732 10.1038/nphoton.2015.69 |
| ContentType | Journal Article |
| DBID | AAYXX CITATION NPM 7X8 |
| DOI | 10.1364/OE.27.036276 |
| DatabaseName | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Physics |
| EISSN | 1094-4087 |
| ExternalDocumentID | 31873410 10_1364_OE_27_036276 |
| Genre | Journal Article |
| GroupedDBID | --- 123 29N 2WC 8SL AAFWJ AAWJZ AAYXX ABGOQ ACGFO ADBBV AEDJG AENEX AFPKN AKGWG ALMA_UNASSIGNED_HOLDINGS ATHME AYPRP AZSQR AZYMN BAWUL BCNDV CITATION CS3 DIK DSZJF DU5 E3Z EBS F5P GROUPED_DOAJ GX1 KQ8 M~E OFLFD OK1 OPJBK OPLUZ OVT P2P RNS ROL ROS TR2 TR6 XSB NPM ROP 7X8 |
| ID | FETCH-LOGICAL-c329t-5e806f09579667f4bf8995fb2198f3d5f6a7dcc6b26182d4d857e09b1c95bcf63 |
| ISICitedReferencesCount | 18 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000503978100021&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1094-4087 |
| IngestDate | Sun Nov 09 09:24:26 EST 2025 Wed Feb 19 02:31:51 EST 2025 Sat Nov 29 06:13:38 EST 2025 Tue Nov 18 21:37:45 EST 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 25 |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c329t-5e806f09579667f4bf8995fb2198f3d5f6a7dcc6b26182d4d857e09b1c95bcf63 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| OpenAccessLink | https://doi.org/10.1364/oe.27.036276 |
| PMID | 31873410 |
| PQID | 2330329351 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2330329351 pubmed_primary_31873410 crossref_citationtrail_10_1364_OE_27_036276 crossref_primary_10_1364_OE_27_036276 |
| PublicationCentury | 2000 |
| PublicationDate | 2019-12-09 2019-Dec-09 20191209 |
| PublicationDateYYYYMMDD | 2019-12-09 |
| PublicationDate_xml | – month: 12 year: 2019 text: 2019-12-09 day: 09 |
| PublicationDecade | 2010 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Optics express |
| PublicationTitleAlternate | Opt Express |
| PublicationYear | 2019 |
| References | Liu (oe-27-25-36276-R36) 2014; 22 Pestourie (oe-27-25-36276-R18) 2018; 26 Jin (oe-27-25-36276-R20) 2007; 55 Liu (oe-27-25-36276-R29) 2018; 5 Liu (oe-27-25-36276-R30) 2018; 18 Wang (oe-27-25-36276-R7) 2019; 9 Piggott (oe-27-25-36276-R24) 2015; 9 Kirkpatrick (oe-27-25-36276-R25) 1983; 220 Malkiel (oe-27-25-36276-R13) 2018 Piggott (oe-27-25-36276-R11) 2017; 7 Fan (oe-27-25-36276-R6) 2019 Molesky (oe-27-25-36276-R3) 2018; 12 Tahersima (oe-27-25-36276-R14) 2019; 9 Wang (oe-27-25-36276-R21) 2011; 28 Asano (oe-27-25-36276-R12) 2018; 26 Christiansen (oe-27-25-36276-R22) 2019; 122 Campbell (oe-27-25-36276-R9) 2019; 9 Sun (oe-27-25-36276-R27) 2018; 26 So (oe-27-25-36276-R5) 2019; 11 Frandsen (oe-27-25-36276-R10) 2016; 9756 Peurifoy (oe-27-25-36276-R17) 2018; 4 Inampudi (oe-27-25-36276-R19) 2018; 112 Forestiere (oe-27-25-36276-R32) 2016; 3 Sigmund (oe-27-25-36276-R23) 2008; 100 Li (oe-27-25-36276-R38) 2019; 27 Ma (oe-27-25-36276-R28) 2018; 12 Chang (oe-27-25-36276-R2) 2018; 26 Chang (oe-27-25-36276-R1) 2017 Chen (oe-27-25-36276-R35) 2017; 25 |
| References_xml | – volume: 7 start-page: 1786 year: 2017 ident: oe-27-25-36276-R11 publication-title: Sci. Rep. doi: 10.1038/s41598-017-01939-2 – volume: 11 start-page: 24264 year: 2019 ident: oe-27-25-36276-R5 publication-title: ACS Appl. Mater. Interfaces doi: 10.1021/acsami.9b05857 – volume: 112 start-page: 241102 year: 2018 ident: oe-27-25-36276-R19 publication-title: Appl. Phys. Lett. doi: 10.1063/1.5033327 – volume: 100 start-page: 153904 year: 2008 ident: oe-27-25-36276-R23 publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.100.153904 – volume: 12 start-page: 659 year: 2018 ident: oe-27-25-36276-R3 publication-title: Nat. Photonics doi: 10.1038/s41566-018-0246-9 – volume: 9 start-page: 1842 year: 2019 ident: oe-27-25-36276-R9 publication-title: Opt. Mater. Express doi: 10.1364/OME.9.001842 – volume: 55 start-page: 556 year: 2007 ident: oe-27-25-36276-R20 publication-title: IEEE Trans. Antennas Propag. doi: 10.1109/TAP.2007.891552 – volume: 18 start-page: 6570 year: 2018 ident: oe-27-25-36276-R30 publication-title: Nano Lett. doi: 10.1021/acs.nanolett.8b03171 – start-page: SF1J-8 year: 2017 ident: oe-27-25-36276-R1 article-title: Inverse design of an ultra-compact mode (de) multiplexer based on subwavelength structure – volume: 5 start-page: 1365 year: 2018 ident: oe-27-25-36276-R29 publication-title: ACS Photonics doi: 10.1021/acsphotonics.7b01377 – volume: 22 start-page: 16178 year: 2014 ident: oe-27-25-36276-R36 publication-title: Opt. Express doi: 10.1364/OE.22.016178 – volume: 26 start-page: 32704 year: 2018 ident: oe-27-25-36276-R12 publication-title: Opt. Express doi: 10.1364/OE.26.032704 – volume: 27 start-page: 16047 year: 2019 ident: oe-27-25-36276-R38 publication-title: Opt. Express doi: 10.1364/OE.27.016047 – volume: 122 start-page: 234502 year: 2019 ident: oe-27-25-36276-R22 publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.122.234502 – volume: 25 start-page: 21358 year: 2017 ident: oe-27-25-36276-R35 publication-title: Opt. Express doi: 10.1364/OE.25.021358 – volume: 220 start-page: 671 year: 1983 ident: oe-27-25-36276-R25 publication-title: Science doi: 10.1126/science.220.4598.671 – volume: 9 start-page: 1368 year: 2019 ident: oe-27-25-36276-R14 publication-title: Sci. Rep. doi: 10.1038/s41598-018-37952-2 – volume: 9 start-page: 469 year: 2019 ident: oe-27-25-36276-R7 publication-title: Opt. Mater. Express doi: 10.1364/OME.9.000469 – volume: 28 start-page: 387 year: 2011 ident: oe-27-25-36276-R21 publication-title: J. Opt. Soc. Am. B doi: 10.1364/JOSAB.28.000387 – start-page: 1 year: 2018 ident: oe-27-25-36276-R13 article-title: Deep learning for the design of nano-photonic structures – volume: 26 start-page: 14678 year: 2018 ident: oe-27-25-36276-R27 publication-title: Opt. Express doi: 10.1364/OE.26.014678 – volume: 4 start-page: eaar4206 year: 2018 ident: oe-27-25-36276-R17 publication-title: Sci. Adv. doi: 10.1126/sciadv.aar4206 – volume: 26 start-page: 24135 year: 2018 ident: oe-27-25-36276-R2 publication-title: Opt. Express doi: 10.1364/OE.26.024135 – start-page: AM4K-4 year: 2019 ident: oe-27-25-36276-R6 article-title: Generating high performance, topologically-complex metasurfaces with neural networks – volume: 3 start-page: 68 year: 2016 ident: oe-27-25-36276-R32 publication-title: ACS Photonics doi: 10.1021/acsphotonics.5b00463 – volume: 12 start-page: 6326 year: 2018 ident: oe-27-25-36276-R28 publication-title: ACS Nano doi: 10.1021/acsnano.8b03569 – volume: 26 start-page: 33732 year: 2018 ident: oe-27-25-36276-R18 publication-title: Opt. Express doi: 10.1364/OE.26.033732 – volume: 9756 start-page: 97560Y year: 2016 ident: oe-27-25-36276-R10 article-title: Inverse design engineering of all-silicon polarization beam splitters – volume: 9 start-page: 374 year: 2015 ident: oe-27-25-36276-R24 publication-title: Nat. Photonics doi: 10.1038/nphoton.2015.69 |
| SSID | ssj0014797 |
| Score | 2.4212098 |
| Snippet | Neural network-based inverse design of nanophotonic device network is computationally and time efficient, but in general suffers the problems of robustness and... |
| SourceID | proquest pubmed crossref |
| SourceType | Aggregation Database Index Database Enrichment Source |
| StartPage | 36276 |
| Title | Robust inverse-design of scattering spectrum in core-shell structure using modified denoising autoencoder neural network |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/31873410 https://www.proquest.com/docview/2330329351 |
| Volume | 27 |
| WOSCitedRecordID | wos000503978100021&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: PRVAON databaseName: Directory of Open Access Journals customDbUrl: eissn: 1094-4087 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014797 issn: 1094-4087 databaseCode: DOA dateStart: 19980101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1094-4087 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014797 issn: 1094-4087 databaseCode: M~E dateStart: 19970101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1ba9swFBZpt5W-jN2bXYIG21NwZ8u2Lo9jZIzBmjE6yJuxZakYGtuL45Kn_fYdSb6klMD2sBcT5BMb_H2cu44QeifBSyYsIB6BKMeLVBB6aaS1lweUcMVSoxLtYRPs4oKvVuL7ZNL2e2FurllZ8t1O1P8ValgDsM3W2X-Ae3goLMBvAB2uADtc_wr4H1XWNmbwv2m4UF5uWzSMT9hIO0vTJhDM_spNu57bLvSN8hrTDzp3w2RNSaG1KYR1lRfa-KignKrCLqXttjKzL80ICjMLExAuXSf5vpu7rO30Z7Wrhw4PSx1X4Sh-ASevBnPgVlUxJhGcJqxGmZWV-dqb2S5LEdgjFnynC5XTrBBHQrDaWddO9bqxAB3FSLynSMGuunNh7qj4kEYAwXJxTti5f0cMsKjXFllQVgxMtD8auqH9sL91hO4RFgujDL_9XgzFp4gJ1u2RgJd92H_VKTrp_3zbkTkQnVgv5fIRetiFF_ijo8VjNFHlE_TAtvnK5inaOXLg2-TAlcYjOXBPDpDCIznwQA5syYF7cuCBHHiPHNiRA3fkeIZ-fl5cfvridWdveDIkYuvFivtU-6aISynTUaYhMI91BgaO6zCPNU1ZLiXNIALnJI9yHjPliyyQIs6kpuFzdFxWpTpDmEdpxkMZqJzIyBd5JgWnmlFwVKWIOJmief8hE9kNpjfno1wnttpKo2S5SAhLHAJT9H6Qrt1AlgNyb3tMEtCYpgyWlqpqm4SE4LaBlxsHU_TCgTU8qQf35cE7r9DpyO_X6Bi-vXqD7subbdFsZuiIrfjMJnZmllR_AMo3lXg |
| linkProvider | ISSN International Centre |
| 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=Robust+inverse-design+of+scattering+spectrum+in+core-shell+structure+using+modified+denoising+autoencoder+neural+network&rft.jtitle=Optics+express&rft.au=Hu%2C+Baiqiang&rft.au=Wu%2C+Bei&rft.au=Tan%2C+Dong&rft.au=Xu%2C+Jing&rft.date=2019-12-09&rft.eissn=1094-4087&rft.volume=27&rft.issue=25&rft.spage=36276&rft_id=info:doi/10.1364%2FOE.27.036276&rft_id=info%3Apmid%2F31873410&rft.externalDocID=31873410 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1094-4087&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1094-4087&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1094-4087&client=summon |