Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205303957> ?p ?o ?g. }
- W3205303957 endingPage "4065" @default.
- W3205303957 startingPage "4057" @default.
- W3205303957 abstract "Deep learning (DL) has emerged as a promising tool for photonic inverse design. Nevertheless, despite the initial success in retrieving spectra of modest complexity with nearly instantaneous readout, DL-assisted design methods often underperform in accuracy compared with advanced optimization techniques and have not proven competitive in handling spectra of practical usefulness. Here, we introduce a tandem optimization model that combines a mixture density network (MDN) and a fully connected (FC) network to inversely design practical thin-film high reflectors. The multimodal nature of the MDN gives access to infinite candidate designs described by probability distributions, which are iteratively sampled and evaluated by the FC network to allow for rapid optimization. We show that the proposed model can retrieve the reflectance spectra of 20-layer thin-film structures. More interestingly, it reproduces with high precision the periodic structures of high reflectors derived from physical principles, even though no such information is included in the training data. Improved designs with extended high-reflectance zones are also demonstrated. Our approach combines the high-efficiency advantage of DL with the optimization-enabled performance improvement, enabling efficient and on-demand inverse design for practical applications." @default.
- W3205303957 created "2021-10-25" @default.
- W3205303957 creator A5010394308 @default.
- W3205303957 creator A5023313653 @default.
- W3205303957 creator A5031103365 @default.
- W3205303957 creator A5058598532 @default.
- W3205303957 creator A5060995156 @default.
- W3205303957 date "2021-10-08" @default.
- W3205303957 modified "2023-10-01" @default.
- W3205303957 title "A mixture-density-based tandem optimization network for on-demand inverse design of thin-film high reflectors" @default.
- W3205303957 cites W2018318430 @default.
- W3205303957 cites W2052256686 @default.
- W3205303957 cites W2074175464 @default.
- W3205303957 cites W2076350013 @default.
- W3205303957 cites W2146381241 @default.
- W3205303957 cites W2165659248 @default.
- W3205303957 cites W2473236422 @default.
- W3205303957 cites W2484513983 @default.
- W3205303957 cites W2540323365 @default.
- W3205303957 cites W2589655892 @default.
- W3205303957 cites W2766162919 @default.
- W3205303957 cites W2775280502 @default.
- W3205303957 cites W2803281408 @default.
- W3205303957 cites W2806536390 @default.
- W3205303957 cites W2808180483 @default.
- W3205303957 cites W2884775584 @default.
- W3205303957 cites W2891797827 @default.
- W3205303957 cites W2914973752 @default.
- W3205303957 cites W2949257317 @default.
- W3205303957 cites W2949960465 @default.
- W3205303957 cites W2962914006 @default.
- W3205303957 cites W2963748309 @default.
- W3205303957 cites W2974878544 @default.
- W3205303957 cites W2982482221 @default.
- W3205303957 cites W2986934761 @default.
- W3205303957 cites W2994313880 @default.
- W3205303957 cites W2996730279 @default.
- W3205303957 cites W3003905418 @default.
- W3205303957 cites W3006582315 @default.
- W3205303957 cites W3008967825 @default.
- W3205303957 cites W3010707275 @default.
- W3205303957 cites W3023907686 @default.
- W3205303957 cites W3035776569 @default.
- W3205303957 cites W3083947857 @default.
- W3205303957 cites W3088687196 @default.
- W3205303957 cites W3092323705 @default.
- W3205303957 cites W3095914940 @default.
- W3205303957 cites W3099853468 @default.
- W3205303957 cites W3100898792 @default.
- W3205303957 cites W3102673610 @default.
- W3205303957 cites W3105195789 @default.
- W3205303957 cites W3112263403 @default.
- W3205303957 cites W3128539297 @default.
- W3205303957 cites W3129644058 @default.
- W3205303957 cites W3133939109 @default.
- W3205303957 cites W3155802603 @default.
- W3205303957 cites W3164210511 @default.
- W3205303957 doi "https://doi.org/10.1515/nanoph-2021-0392" @default.
- W3205303957 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36425324" @default.
- W3205303957 hasPublicationYear "2021" @default.
- W3205303957 type Work @default.
- W3205303957 sameAs 3205303957 @default.
- W3205303957 citedByCount "14" @default.
- W3205303957 countsByYear W32053039572022 @default.
- W3205303957 countsByYear W32053039572023 @default.
- W3205303957 crossrefType "journal-article" @default.
- W3205303957 hasAuthorship W3205303957A5010394308 @default.
- W3205303957 hasAuthorship W3205303957A5023313653 @default.
- W3205303957 hasAuthorship W3205303957A5031103365 @default.
- W3205303957 hasAuthorship W3205303957A5058598532 @default.
- W3205303957 hasAuthorship W3205303957A5060995156 @default.
- W3205303957 hasBestOaLocation W32053039571 @default.
- W3205303957 hasConcept C108597893 @default.
- W3205303957 hasConcept C11413529 @default.
- W3205303957 hasConcept C114563136 @default.
- W3205303957 hasConcept C120665830 @default.
- W3205303957 hasConcept C121332964 @default.
- W3205303957 hasConcept C126255220 @default.
- W3205303957 hasConcept C1276947 @default.
- W3205303957 hasConcept C134306372 @default.
- W3205303957 hasConcept C135252773 @default.
- W3205303957 hasConcept C137836250 @default.
- W3205303957 hasConcept C159985019 @default.
- W3205303957 hasConcept C192562407 @default.
- W3205303957 hasConcept C207467116 @default.
- W3205303957 hasConcept C20788544 @default.
- W3205303957 hasConcept C2524010 @default.
- W3205303957 hasConcept C2777814067 @default.
- W3205303957 hasConcept C33923547 @default.
- W3205303957 hasConcept C41008148 @default.
- W3205303957 hasConcept C4839761 @default.
- W3205303957 hasConcept C49040817 @default.
- W3205303957 hasConcept C76155785 @default.
- W3205303957 hasConceptScore W3205303957C108597893 @default.
- W3205303957 hasConceptScore W3205303957C11413529 @default.
- W3205303957 hasConceptScore W3205303957C114563136 @default.
- W3205303957 hasConceptScore W3205303957C120665830 @default.
- W3205303957 hasConceptScore W3205303957C121332964 @default.