The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.
The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.
Patent No.:
Date of Patent:
Feb. 14, 2023
Filed:
Sep. 27, 2019
Applicant:
Snap Inc., Santa Monica, CA (US);
Inventors:
Enxu Yan, Los Altos, CA (US);
Sergey Tulyakov, Marina del Rey, CA (US);
Aleksei Podkin, London, GB;
Aleksei Stoliar, Marina del Rey, CA (US);
Assignee:
Snap Inc., Santa Monica, CA (US);
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 3/08 (2006.01); G06N 3/082 (2023.01); G06N 3/04 (2023.01); G06F 17/16 (2006.01); G06T 7/10 (2017.01);
U.S. Cl.
CPC ...
G06N 3/082 (2013.01); G06F 17/16 (2013.01); G06N 3/04 (2013.01); G06T 7/10 (2017.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01);
Abstract
A neural network pruning system can sparsely prune neural network models using an optimizer based approach that is agnostic to the model architecture being pruned. The neural network pruning system can prune by operating on the parameter vector of the full model and the gradient vector of the loss function with respect to the model parameters. The neural network pruning system can iteratively update parameters based on the gradients, while zeroing out as many parameters as possible based a preconfigured penalty.