Hierarchical machine learning architecture including master engine supported by distributed light-weight real-time edge engines
AssigneeSingularity Systems Inc.
InventorTianhao Wu
Life of this patent
Estimating the term…
Abstract
A system and method relate to a processing device implementing a master artificial intelligence (AI) engine to receive, from each of one or more real-time AI engines, a machine learning algorithm, parameters associated with the machine learning algorithm, and features employed to train the parameters, receive labeled data used to train the parameters associated with the machine learning algorithm, and construct, based on a combination rule, a master machine learning model using the features, the machine learning algorithm, and the parameters associated with the machine learning algorithm received from each of the one or more real-time AI engines.
Claims20
A hierarchical machine learning system implemented by one or more computers comprising:
- a storage device;
- and
- a processing device implementing a master artificial intelligence (AI) engine to:
- receive, from each of one or more real-time AI engines, a machine learning algorithm, parameters associated with the machine learning algorithm, and features employed to train the parameters;
- receive, from each of the one or more real-time AI engines, labeled data used to calculate the features;
- and
- construct, based on a combination rule, a master machine learning model using the features, the machine learning algorithm, and the parameters associated with the machine learning algorithm received from each of the one or more real-time AI engines.
A method of hierarchical machine learning, the method comprising:
- receiving, by a processing device from each of one or more real-time AI engines, a machine learning algorithm, parameters associated with the machine learning algorithm, and features employed to train the parameters;
- receiving, from each of the one or more real-time AI engines, labeled data used to calculate the features;
- and
- constructing, based on a combination rule, a master machine learning model using the features, the machine learning algorithm, and the parameters associated with the machine learning algorithm received from each of the one or more real-time AI engines.
20-39. (canceled)
Dependencies are inferred from the claim text.