logo

For the Inventor, By the Inventor

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.:

US 11301571 B1

PDFFull Text
Date of Patent:
Apr. 12, 2022

Filed:

May. 25, 2021

Neural-network training using secure data processing

Applicant:

Via Science, Inc., Somerville, MA (US);

Inventors:

Jeremy Taylor, Montreal, CA;

Jesús Alejandro Cárdenes Cabré, Montreal, CA;

Kai Chung Cheung, Markham, CA;

John Christopher Muddle, Montreal, CA;

Colin Gounden, Cambridge, MA (US);

Assignee:

VIA SCIENCE, INC., Somerville, MA (US);

Attorney:

Pierce Atwood LLP

Primary Examiner:

J Brant Murphy

Assistant Examiner:

Stephen T Gundry

Int. Cl.
CPC ...
G06F 21/60 (2013.01); G06F 11/34 (2006.01); G06N 3/10 (2006.01); G06F 7/58 (2006.01); G06N 3/04 (2006.01); H04L 9/00 (2022.01); H04L 9/30 (2006.01); G06N 20/10 (2019.01); G06Q 20/38 (2012.01); G06F 21/62 (2013.01); G06N 3/08 (2006.01);
U.S. Cl.
CPC ...
G06F 21/602 (2013.01); G06F 7/588 (2013.01); G06F 11/3466 (2013.01); G06F 21/6245 (2013.01); G06N 3/0445 (2013.01); G06N 3/0454 (2013.01); G06N 3/0472 (2013.01); G06N 3/0481 (2013.01); G06N 3/084 (2013.01); G06N 3/10 (2013.01); G06N 20/10 (2019.01); G06Q 20/3823 (2013.01); G06Q 20/3829 (2013.01); H04L 9/008 (2013.01); H04L 9/3066 (2013.01); G06F 7/58 (2013.01);
Abstract

Computer instructions corresponding to a neural-network model are received and encrypted using an encryption technique. Training data encrypted using the encryption technique is received from a data source. The model is trained using the training data using, for example, a gradient descent technique. If the model performs in accordance with a quality metric, it is sent to a device of a model user.

Find Patent Forward Citations

Taylor, Jeremy. (2022). Neural-network training using secure data processing (U.S. Patent No. 11301571). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/11301571

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Loading…