US 12,422,302 B2
Integrated circuit spectrometer
Anmin Kong, Singapore (SG); Shaonan Zheng, Singapore (SG); and Lennon Yao Ting Lee, Singapore (SG)
Assigned to Agency for Science, Technology and Research, Singapore (SG)
Appl. No. 18/550,949
Filed by Agency for Science, Technology and Research, Singapore (SG)
PCT Filed Mar. 17, 2021, PCT No. PCT/SG2021/050141
§ 371(c)(1), (2) Date Sep. 15, 2023,
PCT Pub. No. WO2022/197240, PCT Pub. Date Sep. 22, 2022.
Prior Publication US 2024/0142303 A1, May 2, 2024
Int. Cl. G06N 3/048 (2023.01); G01J 3/02 (2006.01); G01J 3/12 (2006.01); G01J 3/28 (2006.01); G02B 6/293 (2006.01); G06N 3/084 (2023.01)
CPC G01J 3/0259 (2013.01) [G01J 3/12 (2013.01); G01J 3/2803 (2013.01); G06N 3/048 (2023.01); G06N 3/084 (2013.01); G01J 2003/1213 (2013.01); G02B 6/29343 (2013.01)] 12 Claims
OG exemplary drawing
 
1. An integrated circuit spectrometer comprising:
a photonic circuit comprising:
an optical input port for receiving light from a light source; and
a filter array of microring resonators in optical communication with the optical input port, each microring resonator being characterized by a different series of resonance wavelengths;
a plurality of detectors, each of which is associated with one of said microring resonators to detect photons from an output of the microring resonator; and
at least one processor configured to reconstruct, from signals received at the plurality of detectors, an input spectrum of light received at the optical input port using an artificial neural network, the artificial neural network comprising:
an input layer having a number of neurons equal to a number of detectors of the plurality of detectors;
an output layer having a number of neurons equal to a number of wavelength points in the input spectrum such that the number of neurons in the output layer is greater than the number of neurons in the input layer;
a plurality of hidden layers; and
a plurality of batch normalization layers such that each hidden layer of the plurality of hidden layers feeds into a respective batch normalization layer of the plurality of batch normalization layers.