Back to results
US 11,386,342 B2Granted
Model interpretation
AssigneeH2O.ai Inc.
InventorsMark Chan, Navdeep Gill, Patrick Hall
Life of this patent
Estimating the term…
Abstract
Input data associated with a machine learning model is classified into a plurality of clusters. A plurality of linear surrogate models are generated. One of the plurality of linear surrogate models corresponds to one of the plurality of clusters. A linear surrogate model is configured to output a corresponding prediction based on input data associated with a corresponding cluster. Prediction data associated with the machine learning model and prediction data associated with the plurality of linear surrogate models are outputted.
Claims20
A method, comprising:
- classifying input data associated with a machine learning model into a plurality of clusters;
- generating a plurality of linear surrogate models and one or more non-linear surrogate models, wherein one of the plurality of linear surrogate models corresponds to one of the plurality of clusters, wherein a linear surrogate model is configured to output a corresponding prediction based on input data associated with a corresponding cluster, wherein each of the plurality of linear surrogate models and the one or more non-linear surrogate models approximate an output of the machine learning model;
- outputting the prediction data associated with the machine learning model, prediction data associated with the plurality of linear surrogate models, and prediction data associated with the one or more non-linear surrogate models;
- determining that the prediction data associated with one of the linear surrogate models correlates with the predication data associated with machine learning model and the prediction data associated with one of the non-linear surrogate models correlates with the prediction data associated with the machine learning model;
- and
- utilizing the one of the linear surrogate models and the one of the non-linear surrogate models to provide an indication of one or more input features of the input data that influenced the prediction data associated with the machine learning model.
3 more elements
A system, comprising:
- a processor configured to:
- classify input data associated with a machine learning model into a plurality of clusters;
- generate a plurality of linear surrogate models and one or more non-linear surrogate models, wherein one of the plurality of linear surrogate models corresponds to one of the plurality of clusters, wherein a linear surrogate model is configured to output a corresponding prediction based on input data associated with a corresponding cluster, wherein each of the plurality of linear surrogate models and the one or more non-linear surrogate models approximate an output of the machine learning model;
- output the prediction data associated with the machine learning model, prediction data associated with the plurality of linear surrogate models, and prediction data associated with the one or more non-linear surrogate models;
- determine that the prediction data associated with one of the linear surrogate models correlates with the predication data associated with machine learning model and the prediction data associated with one of the non-linear surrogate models correlates with the prediction data associated with the machine learning model;
- and
- utilize the one of the linear surrogate models and the one of the non-linear surrogate models to provide an indication of one or more input features of the input data that influenced the prediction data associated with the machine learning model;
- and
- a memory coupled to the processor and configured to provide the processor with instructions.
6 more elements
A computer program product, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
- classifying input data associated with a machine learning model into a plurality of clusters;
- generating a plurality of linear surrogate models and one or more non-linear surrogate models, wherein one of the plurality of linear surrogate models corresponds to one of the plurality of clusters, wherein a linear surrogate model is configured to output a corresponding prediction based on input data associated with a corresponding cluster, wherein each of the plurality of linear surrogate models and the one or more non-linear surrogate models approximate an output of the machine learning model;
- outputting the prediction data associated with the machine learning model, prediction data associated with the plurality of linear surrogate models, and prediction data associated with the one or more non-linear surrogate models;
- determining that the prediction data associated with one of the linear surrogate models correlates with the predication data associated with machine learning model and the prediction data associated with one of the non-linear surrogate models correlates with the prediction data associated with the machine learning model;
- and
- utilizing the one of the linear surrogate models and the one of the non-linear surrogate models to provide an indication of one or more input features of the input data that influenced the prediction data associated with the machine learning model.
3 more elements
Dependencies are inferred from the claim text.