	US 11,875,557 B2
	Polynomial convolutional neural network with early fan-out
Felix Juefei Xu, Pittsburgh, PA (US); and Marios Savvides, Pittsburgh, PA (US)
Assigned to Carnegie Mellon University, Pittsburgh, PA (US)
Appl. No. 16/976,409
Filed by CARNEGIE MELLON UNIVERSITY, Pittsburgh, PA (US)
PCT Filed Apr. 29, 2019, PCT No. PCT/US2019/029619 § 371(c)(1), (2) Date Aug. 27, 2020, PCT Pub. No. WO2019/210295, PCT Pub. Date Oct. 31, 2019.
Claims priority of provisional application 62/762,292, filed on Apr. 27, 2018.
Prior Publication US 2021/0089844 A1, Mar. 25, 2021
Int. Cl. G06V 10/82 (2022.01); G06N 3/084 (2023.01); G06N 3/08 (2023.01); G06V 10/44 (2022.01); G06F 18/21 (2023.01); G06F 18/25 (2023.01); G06F 18/2135 (2023.01); G06N 3/048 (2023.01); G06F 18/2413 (2023.01); G06N 3/045 (2023.01)

CPC G06V 10/82 (2022.01) [G06F 18/21 (2023.01); G06F 18/21355 (2023.01); G06F 18/2414 (2023.01); G06F 18/253 (2023.01); G06N 3/045 (2023.01); G06N 3/048 (2023.01); G06N 3/08 (2013.01); G06N 3/084 (2013.01); G06V 10/454 (2022.01)]

9 Claims

1. A method for training a neural network comprising, for each convolution layer in the neural network:

receiving a gradient function;

adjusting a seed convolutional filter based on the gradient function;

generating a plurality of augmented convolutional filters, wherein each weight of each augmented convolutional filter is generated by applying a polynomial to one or more weights of the seed convolutional filter;

receiving an input;

generating a plurality of response maps based on convolutions of the input with the seed convolutional filter and each of the plurality of augmented convolutional filters; and

generating a feature map based on the plurality of response maps.