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. 06, 2025

Filed:

Sep. 14, 2020
Applicant:

Cognizant Technology Solutions U.s. Corporation, College Station, TX (US);

Inventors:

Santiago Gonzalez, Denver, CO (US);

Risto Miikkulainen, Stanford, CA (US);

Assignee:

Cognizant Technology Solutions U.S. Corp., College Station, TX (US);

Attorneys:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06F 17/11 (2005.12); G06F 17/16 (2005.12); G06F 17/18 (2005.12); G06F 18/10 (2022.12); G06F 18/21 (2022.12); G06N 3/08 (2022.12); G06N 7/01 (2022.12); G06V 10/72 (2021.12); G06V 10/764 (2021.12); G06V 10/776 (2021.12); G06V 10/82 (2021.12);
U.S. Cl.
CPC ...
G06F 17/11 (2012.12); G06F 17/16 (2012.12); G06F 17/18 (2012.12); G06F 18/10 (2022.12); G06F 18/217 (2022.12); G06N 3/08 (2012.12); G06N 7/01 (2022.12); G06V 10/72 (2021.12); G06V 10/764 (2021.12); G06V 10/776 (2021.12); G06V 10/82 (2021.12);
Abstract

A process for optimizing loss functions includes progressively building better sets of parameters for loss functions represented as multivariate Taylor expansions in accordance with an iterative process. The optimization process is built upon CMA-ES. At each generation (i.e., each CMA-ES iteration), a new set of candidate parameter vectors is sampled. These candidate parameter vectors are sampled from a multivariate Gaussian distribution representation that is modeled by the CMA-ES covariance matrix and the current mean vector. The candidates are then each evaluated by training a model (neural network) using the candidates and determining a fitness value for each candidate against a validation data set.


Find Patent Forward Citations

Loading…