Inverse Design of Photonic Devices with Strict Foundry Fabrication Constraints

We introduce a new method for inverse design of nanophotonic devices which guarantees that resulting designs satisfy strict length scale constraints - including minimum width and spacing required by commercial semiconductor foundries. The adopts several concepts from machine learning to transform the problem topology optimization with an unconstrained stochastic gradient problem. Specifically, we conditional generator feasible adopt straight-through estimator backpropagation gradients latent design. demonstrate performance reliability our designing common integrated photonic components.