	US 12,293,293 B2
	Machine learning using structurally regularized convolutional neural network architecture
Pavel Sinha, Brossard (CA); Zeljko Zilic, Verdun (CA); and Ioannis Psaromiligkos, Montreal (CA)
Assigned to AARISH TECHNOLOGIES, Brossard (CA)
Appl. No. 17/280,846
Filed by Pavel Sinha, Brossard (CA)
PCT Filed Sep. 30, 2019, PCT No. PCT/IB2019/001071 § 371(c)(1), (2) Date Mar. 26, 2021, PCT Pub. No. WO2020/065403, PCT Pub. Date Apr. 2, 2020.
Claims priority of provisional application 62/837,957, filed on Apr. 24, 2019.
Claims priority of provisional application 62/737,960, filed on Sep. 28, 2018.
Prior Publication US 2022/0004810 A1, Jan. 6, 2022
Int. Cl. G06N 3/08 (2023.01); G06F 18/214 (2023.01); G06N 3/045 (2023.01); G06N 3/0464 (2023.01); G06N 3/084 (2023.01); G06V 10/44 (2022.01); G06V 10/52 (2022.01); G06V 10/82 (2022.01)

CPC G06N 3/084 (2013.01) [G06F 18/214 (2023.01); G06N 3/045 (2023.01); G06N 3/0464 (2023.01); G06N 3/08 (2013.01); G06V 10/454 (2022.01); G06V 10/52 (2022.01); G06V 10/82 (2022.01)]

40 Claims

1. An apparatus for pattern recognition, comprising:

a memory; and

a processor coupled to the memory and configured to:

receive data comprising a pattern to be recognized;

decompose the data into a plurality of sub-bands using an adaptive transform;

process each of the plurality of sub-bands with a respective convolutional neural network (CNN) to generate a plurality of outputs, wherein each of the CNNs operates independently of the other CNNs;

aggregate the outputs of the CNNs;

train, using the aggregated output, the adaptive transform; and

train, using the aggregated output, the CNNs to recognize the pattern.