CPC G06N 3/08 (2013.01) [B82Y 40/00 (2013.01); G01N 21/21 (2013.01); G01N 21/31 (2013.01); G06N 3/04 (2013.01); G06N 3/048 (2023.01); G06N 3/086 (2013.01); G06N 3/126 (2013.01)] | 20 Claims |
1. A method of designing a nanostructure, comprising:
receiving a synthetic far field optical response and material properties;
feeding said synthetic far field optical response and material properties to an artificial neural network having at least three hidden layers and being trained specifically to provide output describing shapes of nanostructures; and
extracting from said output of said artificial neural network a shape of a nanostructure corresponding to said far field optical response;
wherein said artificial neural network comprises a geometry predicting subnetwork trained to predict a geometry based on spectra and a spectrum predicting subnetwork trained to predict spectra based on geometry.
|