Research / 2020 / Article / Fig 3

Research Article

Probability-Density-Based Deep Learning Paradigm for the Fuzzy Design of Functional Metastructures

Figure 3

Example II of the PDN-based inverse design and experimental demonstration. (a) The output mixture Gaussian for another type of transmission spectrum, which is visualized in a reduced 2D plot. (b) The exact positions of four local maxima visualized by the contour diagram, where the maxima at , , , and correspond to four different metastructures. (c) Comparison among the target transmission spectra, the PDN predicted, and the experimentally measured ones for the metastructures , , , and from the top down. The radii of channels in the labelled structure and the predicted structures are also presented. Each predicted , , , and has different radii, but all get very similar desired transmissions to the target ones.

Please note that the Table of Contents page is currently not displaying content. We are working to fix this issue as soon as possible and apologize for the inconvenience.