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.

Date of Patent:
May. 24, 2022

Filed:

Oct. 31, 2019
Applicant:

Nvidia Corporation, Santa Clara, CA (US);

Inventors:

Larry Robert Dennison, Mendon, MA (US);

Benjamin Klenk, San Jose, CA (US);

Assignee:

NVIDIA Corporation, Santa Clara, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/62 (2022.01); G06N 3/08 (2006.01); G06F 7/483 (2006.01); G06F 9/38 (2018.01); G06N 3/04 (2006.01);
U.S. Cl.
CPC ...
G06K 9/6257 (2013.01); G06F 7/483 (2013.01); G06F 9/3885 (2013.01); G06K 9/6265 (2013.01); G06K 9/6298 (2013.01); G06N 3/0481 (2013.01); G06N 3/08 (2013.01);
Abstract

A technique for performing data parallel training of a neural network model is disclosed that incorporates batch normalization techniques using partial populations to generate normalization parameters. The technique involves processing, by each processor of a plurality of processors in parallel, a first portion of a sub-batch of training samples allocated to the processor to generate activations for the first portion of the sub-batch. Each processor analyzes the activations and transmits statistical measures for the first portion to an additional processor that reduces the statistical measures from multiple processors to generate normalization parameters for a partial population of the training samples that includes the first portion from each of the plurality of processors. The normalization parameters are then transmitted back to each of the processors to normalize the activations for both the first portion and a second portion of the sub-batch of training samples allocated to each processor.


Find Patent Forward Citations

Loading…