Free-form integration of machine learning model primitives
AssigneeInternational Business Machines Corporation
InventorsLior Horesh, Giacomo Nannicini, Oktay Gunluk, Sanjeeb Dash, Parikshit Ram, Alexander Gray
Life of this patent
Estimating the term…
Abstract
A processor may include a set of primitive operators, receive a set of data-driven operators, at least one of the set of data-driven operators including a machine learning model, and receive an input-output data pair set. Based on a grammar specifying rules for linking the set of primitive operators and the set of data-driven operators, the processor may search among the set of primitive operators and the set of data-driven operators to find a symbolic model that fits the input-output data set.
Claims20
A computer-implemented method comprising:
- receiving a set of primitive operators;
- receiving a set of data-driven operators, at least one of the set of data-driven operators including a machine learning model;
- receiving an input-output data pair set;
- and
- based on a grammar specifying rules for linking the set of primitive operators and the set of data-driven operators, searching among the set of primitive operators and the set of data-driven operators to find a symbolic model that fits the input-output data pair set, the symbolic model including a combination of at least one primitive operator and at least one data-driven operator whose parameters are learned.
A system comprising:
- a hardware processor;
- and
- a memory device coupled with the hardware processor;
- the hardware processor configured to at least:
- receive a set of primitive operators;
- receive a set of data-driven operators, at least one of the set of data-driven operators including a machine learning model;
- receive an input-output data pair set;
- based on a grammar specifying rules for linking the set of primitive operators and the set of data-driven operators, search among the set of primitive operators and the set of data-driven operators to find a symbolic model that fits the input-output data pair set, the symbolic model including a combination of at least one primitive operator and at least one data-driven operator whose parameters are learned.
A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to:
- receive a set of primitive operators;
- receive a set of data-driven operators, at least one of the set of data-driven operators including a machine learning model;
- receive an input-output data pair set;
- and
- based on a grammar specifying rules for linking the set of primitive operators and the set of data-driven operators, search among the set of primitive operators and the set of data-driven operators to find a symbolic model that fits the input-output data pair set, the symbolic model including a combination of at least one primitive operator and at least one data-driven operator whose parameters are learned.
Dependencies are inferred from the claim text.