Journal
NANOPHOTONICS
Volume 9, Issue 5, Pages 1059-1069Publisher
WALTER DE GRUYTER GMBH
DOI: 10.1515/nanoph-2019-0330
Keywords
simulator-based training; generative networks; neural networks; adjoint variable method; global optimization
Categories
Funding
- U.S. Air Force [FA9550-18-1-0070]
- Office of Naval Research [N00014-16-1-2630]
- David and Lucile Packard Foundation
Ask authors/readers for more resources
Metasurfaces are subwavelength-structured artificial media that can shape and localize electromagnetic waves in unique ways. The inverse design of these devices is a non-convex optimization problem in a high dimensional space, making global optimization a major challenge. We present a new type of population-based global optimization algorithm for metasurfaces that is enabled by the training of a generative neural network. The loss function used for backpropagation depends on the generated pattern layouts, their efficiencies, and efficiency gradients, which are calculated by the adjoint variables method using forward and adjoint electromagnetic simulations. We observe that the distribution of devices generated by the network continuously shifts towards high performance design space regions over the course of optimization. Upon training completion, the best generated devices have efficiencies comparable to or exceeding the best devices designed using standard topology optimization. Our proposed global optimization algorithm can generally apply to other gradient-based optimization problems in optics, mechanics, and electronics.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available