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.:
Date of Patent:
Dec. 12, 2023
Filed:
Sep. 19, 2022
Applicant:
Nvidia Corporation, Santa Clara, CA (US);
Inventor:
Bernhard Firner, Highland Park, NJ (US);
Assignee:
NVIDIA Corporation, Santa Clara, CA (US);
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G01S 7/41 (2006.01); G06N 3/08 (2023.01); G06N 3/04 (2023.01); G05D 1/00 (2006.01); G05D 1/02 (2020.01); G06F 18/214 (2023.01); G06F 18/24 (2023.01); G06F 18/213 (2023.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/17 (2022.01); G06V 20/10 (2022.01); G06V 20/56 (2022.01);
U.S. Cl.
CPC ...
G01S 7/417 (2013.01); G05D 1/0088 (2013.01); G05D 1/0221 (2013.01); G05D 1/0251 (2013.01); G06F 18/213 (2023.01); G06F 18/214 (2023.01); G06F 18/24 (2023.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/17 (2022.01); G06V 20/176 (2022.01); G06V 20/56 (2022.01); G05D 2201/0213 (2013.01);
Abstract
A neural network is trained to focus on a domain of interest. For example, in a pre-training phase, the neural network in trained using synthetic training data, which is configured to omit or limit content less relevant to the domain of interest, by updating parameters of the neural network to improve the accuracy of predictions. In a subsequent training phase, the pre-trained neural network is trained using real-world training data by updating only a first subset of the parameters associated with feature extraction, while a second subset of the parameters more associated with policies remains fixed.