Automatic combinatoric feature generation for enhanced machine learning
AssigneeInternational Business Machines Corporation
InventorsWillie Robert Patten, Jr., Eugene Irving Kelton, Yi-Hui Ma, Jacob McPherson
Life of this patent
Estimating the term…
Abstract
An approach is provided that automatically computes a number of feature combinations based on a set of subject matter fields that are selected from a set of subject matter fields and further based on qualifiers that correspond to the selected set of subject matter fields. A model in an artificial intelligence (AI) system is then trained using the computed plurality of feature combinations.
Claims20
A method implemented by an information handling system that includes a processor and a memory accessible by the processor, the method comprising:
- automatically computing a plurality of feature combinations based on a set of subject matter fields selected from a plurality of subject matter fields and one or more qualifiers that correspond to the selected set of subject matter fields;
- training a model in an artificial intelligence (AI) system using the computed plurality of feature combinations;
- requesting a dataset from the trained model of the AI system, wherein the request includes a selected one of the feature combinations and a basis to apply to the selected feature combination;
- and
- receiving, from the AI system, the requested dataset.
An information handling system comprising:
- one or more processors;
- a memory coupled to at least one of the processors;
- and
- a set of computer program instructions stored in the memory and executed by at least one of the processors in order to perform actions comprising:
- automatically computing a plurality of feature combinations based on a set of subject matter fields selected from a plurality of subject matter fields and one or more qualifiers that correspond to the selected set of subject matter fields;
- and
- training a model in an artificial intelligence (AI) system using the computed plurality of feature combinations;
- requesting a dataset from the trained model of the AI system, wherein the request includes a selected one of the feature combinations and a basis to apply to the selected feature combination;
- and
- receiving, from the AI system, the requested dataset.
A computer program product stored in a computer readable storage medium, comprising computer program code that, when executed by an information handling system, performs actions comprising:
- automatically computing a plurality of feature combinations based on a set of subject matter fields selected from a plurality of subject matter fields and one or more qualifiers that correspond to the selected set of subject matter fields;
- and
- training a model in an artificial intelligence (AI) system using the computed plurality of feature combinations;
- requesting a dataset from the trained model of the AI system, wherein the request includes a selected one of the feature combinations and a basis to apply to the selected feature combination;
- and
- receiving, from the AI system, the requested dataset.
Dependencies are inferred from the claim text.