Artificial intelligence supported material design for tailored image transformations

Abstract

Neural network based classifiers have been shown to suffer from image perturbations in the form of 2-dimensional transformations. These transformations lack physical constraints making them less of a practical concern and more of a theoretical interest. This paper pushes to produce 3-dimensional materials to mimic these 2-dimensional image transformations by using artificial neural networks to regress material parameters. The neural networks are trained on simulation data from full-wave simulations and physics-based ray tracing simulations. Two neural network models are developed to regress material parameters of a common transformation optics solution, and a Gaussian blur, respectively. The model trained for the transformation optics solution was able to find a unique material solution whose simulated waveform generally matches an analytical solution. The model trained for the Gaussian blur was unable to find an adequate material solution for the image transformation possibly due to the constraints placed on the regression by the ray tracing simulation. Finally, a framework is proposed to combine the ray tracing and full-wave simulations to produce more accurate data, enabling a better regression of material parameters for image transformations.