Deep-learning enabled photonic nanostructure discovery in arbitrarily large shape sets <i>via</i> linked latent space representation learning
Sudhanshu Singh, R. Kumar, Soumyashree S. Panda, Ravi S. Hegde
Abstract
A cross-linked autoencoder neural network for photonics nanostructure discovery effectively links geometry and spectra representations. This approach aids in rapid multiple solution inverse design and assessing their fabrication sensitivity.
Topics & Concepts
AutoencoderNanostructurePhotonicsRepresentation (politics)Artificial neural networkDeep learningPhotonic crystalSpace (punctuation)Sensitivity (control systems)Computer scienceInverseFeature learningNanotechnologyArtificial intelligenceMaterials scienceMathematicsElectronic engineeringEngineeringOptoelectronicsGeometryLawPoliticsPolitical scienceOperating systemPhotonic Crystals and ApplicationsOptical Coatings and GratingsNonlinear Optical Materials Studies