US 11,676,004 B2
Architecture optimized training of neural networks
Kristof Denolf, Los Gatos, CA (US); and Kornelis A. Vissers, Sunnyvale, CA (US)
Assigned to XILINX, INC., San Jose, CA (US)
Filed by Xilinx, Inc., San Jose, CA (US)
Filed on Aug. 15, 2017, as Appl. No. 15/677,311.
Prior Publication US 2019/0057305 A1, Feb. 21, 2019
Int. Cl. G06N 3/08 (2023.01); G06N 3/084 (2023.01); G06N 3/063 (2023.01); G06N 3/04 (2023.01)
CPC G06N 3/08 (2013.01) [G06N 3/04 (2013.01); G06N 3/063 (2013.01); G06N 3/084 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method of optimizing a neural network having a plurality of layers, the method comprising:
obtaining architecture constraints for circuitry of an inference platform that implements the neural network, wherein the architecture constraints comprise a first architecture constraint based on structure of the circuitry of the inference platform and a related data parameter constraint;
training the neural network on a training platform using the architecture constraints to generate network parameters and feature maps for the plurality of layers; and
constraining, during the training of the neural network, the network parameters, the feature maps, or both the network parameters and the feature maps, based on the architecture constraints.