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:
Oct. 03, 2023

Filed:

Aug. 25, 2020
Applicant:

Google Llc, Mountain View, CA (US);

Inventors:

Ruiqi Guo, Elmhurst, NY (US);

David Simcha, Jersey City, NJ (US);

Quan Geng, Jersey City, NJ (US);

Felix Chern, New York, NY (US);

Sanjiv Kumar, Jericho, NY (US);

Xiang Wu, Berkeley, CA (US);

Assignee:

GOOGLE LLC, Mountain View, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 16/20 (2019.01); G06F 16/906 (2019.01); G06F 16/25 (2019.01); H03M 7/30 (2006.01); G06F 16/2457 (2019.01);
U.S. Cl.
CPC ...
G06F 16/906 (2019.01); G06F 16/24578 (2019.01); G06F 16/258 (2019.01); H03M 7/30 (2013.01);
Abstract

Generally, the present disclosure is directed to systems and methods of quantizing a database with respect to a novel loss or quantization error function which applies a weight to an error measurement of quantized elements respectively corresponding to the datapoints in the database. The weight is determined based on the magnitude of an inner product between the respective datapoints and a query compared therewith. In contrast to previous work, embodiments of the proposed loss function are responsive to the expected magnitude of an inner product between the respective datapoints and a query compared therewith and can prioritize error reduction for higher-ranked pairings of the query and the datapoints. Thus, the systems and methods of the present disclosure provide solutions to some of the problems with traditional quantization approaches, which regard all error as equally impactful.


Find Patent Forward Citations

Loading…