Systems and method for enhanced active machine learning through processing of partitioned uncertainty

A non-transitory computer-readable medium having a set of computer-executable instructions embodied thereon that, when executed by a processor, cause the processor to perform a method of improving machine learning of a data set, the method comprising:

• training a predictive model on an initial data set comprising labeled data, wherein the training is performed in an active learning system;
• generating a set of parameters based on the training;
• introducing an unlabeled data set into the predictive model;
• applying the set of parameters to the unlabeled data set;
• generating a set of predictions associated with the applied set of parameters;
• calculating a first uncertainty score and a second uncertainty score associated with the generated set of predictions;
• modifying the data set based on the first uncertainty score;
• and
• modifying the predictive model based on the second uncertainty score.

A system comprising:

• a memory configured to store operations;
• and
• one or more processing devices configured to process the operations, the operations comprising:
• training a predictive model on an initial data set comprising labeled data, wherein the training is performed in an active learning system;
• generating a set of parameters based on the training;
• introducing an unlabeled data set into the predictive model;
• applying the set of parameters to the unlabeled data set;
• generating a set of predictions associated with the applied set of parameters;
• calculating a first uncertainty score and a second uncertainty score associated with the generated set of predictions;
• modifying the data set based on the first uncertainty score;
• and
• modifying the predictive model based on the second uncertainty score.