Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304206722> ?p ?o ?g. }
- W4304206722 endingPage "39582" @default.
- W4304206722 startingPage "39582" @default.
- W4304206722 abstract "Recently, deep reinforcement learning (DRL) for metasurface design has received increased attention for its excellent decision-making ability in complex problems. However, time-consuming numerical simulation has hindered the adoption of DRL-based design method. Here we apply the Deep learning-based virtual Environment Proximal Policy Optimization (DE-PPO) method to design the 3D chiral plasmonic metasurfaces for flexible targets and model the metasurface design process as a Markov decision process to help the training. A well trained DRL agent designs chiral metasurfaces that exhibit the optimal absolute circular dichroism value (typically, ∼ 0.4) at various target wavelengths such as 930 nm, 1000 nm, 1035 nm, and 1100 nm with great time efficiency. Besides, the training process of the PPO agent is exceptionally fast with the help of the deep neural network (DNN) auxiliary virtual environment. Also, this method changes all variable parameters of nanostructures simultaneously, reducing the size of the action vector and thus the output size of the DNN. Our proposed approach could find applications in efficient and intelligent design of nanophotonic devices." @default.
- W4304206722 created "2022-10-11" @default.
- W4304206722 creator A5058299939 @default.
- W4304206722 creator A5059654697 @default.
- W4304206722 creator A5067822524 @default.
- W4304206722 creator A5068932864 @default.
- W4304206722 creator A5084699019 @default.
- W4304206722 date "2022-10-11" @default.
- W4304206722 modified "2023-09-24" @default.
- W4304206722 title "Intelligent design of the chiral metasurfaces for flexible targets: combining a deep neural network with a policy proximal optimization algorithm" @default.
- W4304206722 cites W1950919230 @default.
- W4304206722 cites W1976253857 @default.
- W4304206722 cites W2004215262 @default.
- W4304206722 cites W2070745028 @default.
- W4304206722 cites W2080589920 @default.
- W4304206722 cites W2083926174 @default.
- W4304206722 cites W2144802926 @default.
- W4304206722 cites W2319112622 @default.
- W4304206722 cites W2331487889 @default.
- W4304206722 cites W2487059652 @default.
- W4304206722 cites W2580678987 @default.
- W4304206722 cites W2806536390 @default.
- W4304206722 cites W2916134072 @default.
- W4304206722 cites W2965959756 @default.
- W4304206722 cites W2974250128 @default.
- W4304206722 cites W2989226760 @default.
- W4304206722 cites W2990692647 @default.
- W4304206722 cites W2996016330 @default.
- W4304206722 cites W2997787181 @default.
- W4304206722 cites W3005155031 @default.
- W4304206722 cites W3027512785 @default.
- W4304206722 cites W3031385593 @default.
- W4304206722 cites W3035650744 @default.
- W4304206722 cites W3038151256 @default.
- W4304206722 cites W3039337566 @default.
- W4304206722 cites W3046090201 @default.
- W4304206722 cites W3046425935 @default.
- W4304206722 cites W3081405700 @default.
- W4304206722 cites W3092177130 @default.
- W4304206722 cites W3094548171 @default.
- W4304206722 cites W3102010700 @default.
- W4304206722 cites W3116155568 @default.
- W4304206722 cites W3117606706 @default.
- W4304206722 cites W3161958328 @default.
- W4304206722 cites W3180576418 @default.
- W4304206722 cites W3205338908 @default.
- W4304206722 cites W4206716844 @default.
- W4304206722 cites W4206740990 @default.
- W4304206722 cites W4210374260 @default.
- W4304206722 doi "https://doi.org/10.1364/oe.471629" @default.
- W4304206722 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36298906" @default.
- W4304206722 hasPublicationYear "2022" @default.
- W4304206722 type Work @default.
- W4304206722 citedByCount "2" @default.
- W4304206722 countsByYear W43042067222023 @default.
- W4304206722 crossrefType "journal-article" @default.
- W4304206722 hasAuthorship W4304206722A5058299939 @default.
- W4304206722 hasAuthorship W4304206722A5059654697 @default.
- W4304206722 hasAuthorship W4304206722A5067822524 @default.
- W4304206722 hasAuthorship W4304206722A5068932864 @default.
- W4304206722 hasAuthorship W4304206722A5084699019 @default.
- W4304206722 hasBestOaLocation W43042067221 @default.
- W4304206722 hasConcept C105795698 @default.
- W4304206722 hasConcept C106189395 @default.
- W4304206722 hasConcept C111919701 @default.
- W4304206722 hasConcept C11413529 @default.
- W4304206722 hasConcept C154945302 @default.
- W4304206722 hasConcept C159886148 @default.
- W4304206722 hasConcept C171250308 @default.
- W4304206722 hasConcept C192562407 @default.
- W4304206722 hasConcept C27289702 @default.
- W4304206722 hasConcept C33923547 @default.
- W4304206722 hasConcept C41008148 @default.
- W4304206722 hasConcept C50644808 @default.
- W4304206722 hasConcept C97541855 @default.
- W4304206722 hasConcept C98045186 @default.
- W4304206722 hasConceptScore W4304206722C105795698 @default.
- W4304206722 hasConceptScore W4304206722C106189395 @default.
- W4304206722 hasConceptScore W4304206722C111919701 @default.
- W4304206722 hasConceptScore W4304206722C11413529 @default.
- W4304206722 hasConceptScore W4304206722C154945302 @default.
- W4304206722 hasConceptScore W4304206722C159886148 @default.
- W4304206722 hasConceptScore W4304206722C171250308 @default.
- W4304206722 hasConceptScore W4304206722C192562407 @default.
- W4304206722 hasConceptScore W4304206722C27289702 @default.
- W4304206722 hasConceptScore W4304206722C33923547 @default.
- W4304206722 hasConceptScore W4304206722C41008148 @default.
- W4304206722 hasConceptScore W4304206722C50644808 @default.
- W4304206722 hasConceptScore W4304206722C97541855 @default.
- W4304206722 hasConceptScore W4304206722C98045186 @default.
- W4304206722 hasFunder F4320321001 @default.
- W4304206722 hasFunder F4320334978 @default.
- W4304206722 hasFunder F4320335787 @default.
- W4304206722 hasIssue "22" @default.
- W4304206722 hasLocation W43042067221 @default.
- W4304206722 hasLocation W43042067222 @default.
- W4304206722 hasOpenAccess W4304206722 @default.
- W4304206722 hasPrimaryLocation W43042067221 @default.