Microsoft technology licensing, llc (20250095814). DETERMINING AND PERFORMING OPTIMAL ACTIONS ON A SYSTEM
DETERMINING AND PERFORMING OPTIMAL ACTIONS ON A SYSTEM
Organization Name
microsoft technology licensing, llc
Inventor(s)
Colleen Tyler of Redmond WA US
Marife Defante of Woodinville WA US
Lisa Lynne Parks of Seattle WA US
DETERMINING AND PERFORMING OPTIMAL ACTIONS ON A SYSTEM
This abstract first appeared for US patent application 20250095814 titled 'DETERMINING AND PERFORMING OPTIMAL ACTIONS ON A SYSTEM
Original Abstract Submitted
in certain examples, a causal inference model is trained on a re-balancing task in a self-supervised manner, using ‘unlabelled’ training data pertaining to multiple domains. rather than approaching casual inference as a domain-specific task (e.g., designing one causal-inference approach for a particular manufacturing application, another for a particular aerospace application, another for a specific medical application etc.,) a general-purpose causal inference mechanism is learned from a large, diverse training set that contains many treatments dataset over many field/applications (e.g., combining manufacturing data, engineering data, medical data etc. in a single dataset used to train a single neural network). in other words, a cross-domain causal inference model is trained, which can then be applied to a dataset in any domain, including domains that were not explicitly encountered by the neural network during training.
