Patent Application Titled 'Training A Classification Model Using Labeled Training Data That Does Not Overlap With Target Classifications For The Classification Model' Published Online (USPTO 20240176852)
Patent Application Titled 'Training A Classification Model Using Labeled Training Data That Does Not Overlap With Target Classifications For The Classification Model' Published Online (USPTO 20240176852)
Reporters obtained the following quote from the background information supplied by the inventors: “This disclosure relates generally to training a classification model, and more specifically to training the classification model using existing training data with labels that do not overlap with classes to be output by the classification model.
NETL
NSTL