Accelerating optics design optimizations with deep learning

Show simple item record Hegde, Ravi S. 2019-07-16T09:58:26Z 2019-07-16T09:58:26Z 2019-06
dc.identifier.citation Hegde, Ravi S., �Accelerating optics design optimizations with deep learning�, Optical Engineering, DOI: 10.1117/1.OE.58.6.065103, vol. 58, no. 6, Jun. 2019. en_US
dc.identifier.issn 0091-3286
dc.description.abstract We show that design optimizations, an integral but time-consuming component of optical engineering, can be significantly sped-up when paired with deep neural networks (DNNs). By using the DNN indirectly for choosing initializations and candidate preselection, our approach obviates the need for large networks, big datasets, long training epochs, and excessive hyperparameter optimization. For a 16-layered thin-film design problem, our surrogate-assisted differential evolution (DE) algorithm is able to achieve similar optimal solutions as that of an unassisted DE using only 10% of the function evaluation budget. Our approach is a promising option for the optimal design of optical devices and systems.
dc.description.statementofresponsibility by Ravi S. Hegde
dc.format.extent vol. 58, no. 6
dc.language.iso en en_US
dc.publisher Society of Photo-optical Instrumentation Engineers en_US
dc.subject Data modeling en_US
dc.subject Optical design en_US
dc.subject Optical engineering en_US
dc.subject Neurons en_US
dc.subject Performance modeling en_US
dc.subject Reflectivity en_US
dc.subject Thin films en_US
dc.subject Optimization (mathematics) en_US
dc.subject Network architectures en_US
dc.subject Neural networks en_US
dc.title Accelerating optics design optimizations with deep learning en_US
dc.type Article en_US
dc.relation.journal Optical Engineering

Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Digital Repository


My Account