Photonics Inverse Design: Pairing Deep Neural Networks With Evolutionary Algorithms
Author:
- 7 August 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Quantum Electronics
- Vol. 26 (1) , 1-8
Abstract
Deep Neural Networks (DNN) have shown early promise for inverse design with their ability to arrive at working designs much faster than conventional optimization techniques. Current approaches, however, require complicated workflows involving training more than one DNN to address the problem of non-uniqueness in the inversion and the emphasis on speed has overshadowed the far more important consideration of solution optimality. We propose and demonstrate a simplified workflow that pairs forward-model DNN with evolutionary algorithms which are widely used for inverse gg design. Our evolutionary search in forward-model space is global and exploits the massive parallelism of modern GPUs for a speedy inversion. We propose a hybrid approach where the DNN is used only for preselection and initialization that is more effective at optimization than a standalone DNN and performs nearly as well as a vanilla evolutionary search with a significantly reduced function evaluation budget. We finally show the utility of an iterative procedure for building the training dataset which further boosts the effectiveness of this approach.Keywords
This publication has 25 references indexed in Scilit:
- Deep learningNature, 2015
- OPTIMAL DESIGN OF GRADED REFRACTIVE INDEX PROFILE FOR BROADBAND OMNIDIRECTIONAL ANTIREFLECTION COATINGS USING GENETIC PROGRAMMINGProgress In Electromagnetics Research, 2014
- Design and realization of advanced multi-index systemsApplied Optics, 2013
- Numerical methods for the design of gradient-index optical coatingsApplied Optics, 2012
- Refractive index profile modelling of dielectric inhomogeneous coatings using effective medium theoriesThin Solid Films, 2008
- A comprehensive survey of fitness approximation in evolutionary computationSoft Computing, 2003
- Optimal single-band normal-incidence antireflection coatingsApplied Optics, 1996
- Some theoretical aspects of thin-film optics and their applicationsApplied Optics, 1993
- Quasi-optimal synthesis for antireflection coatings: a new methodApplied Optics, 1993
- Interspecimen Comparison of the Refractive Index of Fused Silica*,†Journal of the Optical Society of America, 1965