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:
Apr. 30, 2019

Filed:

Sep. 08, 2015
Applicant:

Qualcomm Incorporated, San Diego, CA (US);

Inventors:

Sachin Subhash Talathi, San Diego, CA (US);

David Jonathan Julian, San Diego, CA (US);

Assignee:

QUALCOMM Incorporated, San Diego, CA (US);

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06N 20/00 (2019.01); G06N 3/08 (2006.01); G06N 7/00 (2006.01);
U.S. Cl.
CPC ...
G06N 20/00 (2019.01); G06N 3/08 (2013.01); G06N 3/082 (2013.01); G06N 7/005 (2013.01);
Abstract

Hyper-parameters are selected for training a deep convolutional network by selecting a number of network architectures as part of a database. Each of the network architectures includes one or more local logistic regression layer and is trained to generate a corresponding validation error that is stored in the database. A threshold error for identifying a good set of network architectures and a bad set of network architectures may be estimated based on validation errors in the database. The method also includes choosing a next potential hyper-parameter, corresponding to a next network architecture, based on a metric that is a function of the good set of network architectures. The method further includes selecting a network architecture, from among next network architectures, with a lowest validation error.


Find Patent Forward Citations

Loading…