US 12,136,033 B2
Method and system for characterizing a nanostructure by machine learning
Lior Wolf, Herzlia (IL); Haim Suchowski, Kfar Mordechai (IL); Michael Mrejen, Tel Aviv (IL); Achiya Nagler, Tel Aviv (IL); Itzik Malkiel, Tel Aviv (IL); and Uri Arieli, Tel Aviv (IL)
Assigned to Ramot at Tel-Aviv University Ltd., Tel-Aviv (IL)
Appl. No. 16/484,490
Filed by Ramot at Tel-Aviv University Ltd., Tel-Aviv (IL)
PCT Filed Feb. 9, 2018, PCT No. PCT/IL2018/050149
§ 371(c)(1), (2) Date Aug. 8, 2019,
PCT Pub. No. WO2018/146683, PCT Pub. Date Aug. 16, 2018.
Claims priority of provisional application 62/456,781, filed on Feb. 9, 2017.
Prior Publication US 2020/0003678 A1, Jan. 2, 2020
Int. Cl. G01N 21/21 (2006.01); B82Y 40/00 (2011.01); G01N 21/31 (2006.01); G06N 3/04 (2023.01); G06N 3/048 (2023.01); G06N 3/08 (2023.01); G06N 3/086 (2023.01); G06N 3/126 (2023.01)
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
OG exemplary drawing
 
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.