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:
Mar. 15, 2022
Filed:
Mar. 26, 2020
Applicant:
Robert Bosch Gmbh, Stuttgart, DE;
Inventors:
Melih Kandemir, Stuttgart, DE;
Manuel Haussmann, Heidelberg, DE;
Assignee:
Robert Bosch GmbH, Stuttgart, DE;
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/62 (2006.01); G05D 1/02 (2020.01); G05B 13/02 (2006.01); G05D 1/00 (2006.01); G06N 3/04 (2006.01); G06N 3/08 (2006.01);
U.S. Cl.
CPC ...
G05D 1/0221 (2013.01); G05B 13/027 (2013.01); G05D 1/0088 (2013.01); G06K 9/6256 (2013.01); G06K 9/6278 (2013.01); G06K 9/6296 (2013.01); G06N 3/0472 (2013.01); G06N 3/08 (2013.01); G05D 2201/0216 (2013.01);
Abstract
A trained model is described in the form of a Bayesian neural network (BNN) which provides a quantification of its inference uncertainty during use and which is trained using marginal likelihood maximization. A Probably Approximately Correct (PAC) bound may be used in the training to incorporate prior knowledge and to improve training stability even when the network architecture is deep.