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:
Nov. 29, 2016

Filed:

Dec. 16, 2013
Applicant:

Tencent Technology (Shenzhen) Company Limited, Shenzhen, CN;

Inventors:

Eryu Wang, Shenzhen, CN;

Li Lu, Shenzhen, CN;

Xiang Zhang, Shenzhen, CN;

Haibo Liu, Shenzhen, CN;

Feng Rao, Shenzhen, CN;

Lou Li, Shenzhen, CN;

Shuai Yue, Shenzhen, CN;

Bo Chen, Shenzhen, CN;

Assignee:

TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen, Guangdong Province, CN;

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G10L 15/16 (2006.01); G10L 15/34 (2013.01); G10L 15/06 (2013.01); G06N 3/02 (2006.01);
U.S. Cl.
CPC ...
G10L 15/34 (2013.01); G06N 3/02 (2013.01); G10L 15/063 (2013.01); G10L 15/16 (2013.01);
Abstract

A method and a device for training a DNN model includes: at a device including one or more processors and memory: establishing an initial DNN model; dividing a training data corpus into a plurality of disjoint data subsets; for each of the plurality of disjoint data subsets, providing the data subset to a respective training processing unit of a plurality of training processing units operating in parallel, wherein the respective training processing unit applies a Stochastic Gradient Descent (SGD) process to update the initial DNN model to generate a respective DNN sub-model based on the data subset; and merging the respective DNN sub-models generated by the plurality of training processing units to obtain an intermediate DNN model, wherein the intermediate DNN model is established as either the initial DNN model for a next training iteration or a final DNN model in accordance with a preset convergence condition.


Find Patent Forward Citations

Loading…