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:
Apr. 25, 2023
Filed:
May. 01, 2020
Applicant:
Amazon Technologies, Inc., Seattle, WA (US);
Inventors:
Roman Goldenberg, Haifa, IL;
Miriam Farber, Haifa, IL;
George Leifman, Haifa, IL;
Gerard Guy Medioni, Seattle, WA (US);
Assignee:
Amazon Technologies, Inc., Seattle, WA (US);
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 20/20 (2019.01); G06K 9/62 (2022.01); G06N 7/00 (2023.01);
U.S. Cl.
CPC ...
G06K 9/6262 (2013.01); G06K 9/628 (2013.01); G06N 7/005 (2013.01); G06N 20/20 (2019.01);
Abstract
Described are systems and methods for training machine learning models of an ensemble of models that are de-correlated. For example, two or more machine learning models may be concurrently trained (e.g., co-trained) while adding a decorrelation component to one or both models that decreases the pairwise correlation between the outputs of the models. Unlike traditional approaches, in accordance with the disclosed implementations, only the negative results need to be decorrelated.