Back to results
US 12,217,143 B1Granted
Resolving opaqueness of complex machine learning applications
AssigneeWells Fargo Bank, N.A.
InventorsVijayan N. Nair, Agus Sudjianto, Jie Chen, Kurt Schieding, Linwei Hu, Xiaoyu Liu, Joel Vaughan
Life of this patent
Estimating the term…
Abstract
Computing systems and technical methods that transform data structures and pierce opacity difficulties associated with complex machine learning algorithms are disclosed. Advances include a framework and techniques that include: i) global diagnostics; ii) locally interpretable models LIME-SUP-R and LIME-SUP-D; and iii) explainable neural networks.
Claims19
A computing system comprising:
- a replicator that employs Locally Interpretable Models and Effects based on Supervised Partitioning (LIME-SUP) techniques on a plurality of machine learning-models, comprising at least one machine learning model with opacity issues that include a black box effect, to create a replicated semi-additive index data structure that provides local and global explainability for the black box effect,
- wherein the replicator communicates with a library of interpretable machine learning models, and wherein the created replicated semi-additive index data structure is a neural network based formulation of an additive index model where a neural network of the neural network based formulation is a replicated structured neural network that is trained using mini-batch gradient-based methods, and wherein the black box effect is a non-visible operation, of the at least one machine learning model with the opacity issues, that lacks explainability;
- a translator module that generates a score and a plurality of sub-scores based on the created replicated semi-additive index data structure, wherein generating the score involves ranking a relative effect of a disparity to a plurality of elements of the created replicated semi-additive index data structure, wherein the ranking comprises ranking relative importance of a decomposed effect of the disparity, wherein the score is indicative of a match status to the at least one machine learning model with the opacity issues;
- and
- a graphical user interface that renders selected characteristics of the created replicated semi-additive index data structure to produce a rendering that depicts the local and global explainability for the black box effect of the at least one machine learning model with the opacity issues.
2 more elements
A computing system comprising:
- a replicator that employs Locally Interpretable Models and Effects based on Supervised Partitioning (LIME-SUP) techniques on a plurality of machine learning models comprising at least one machine learning model with opacity issues that include a black box effect, wherein the replicator communicates with a library of interpretable machine learning models to create a replicated semi-additive index data structure that provides local and global explainability for the black box effect, wherein the black box effect is a non-visible operation, of the at least one machine learning model with the opacity issues, that lacks explainability, wherein the replicated semi-additive index data structure is a neural network based formulation of an additive index model where a neural network of the neural network based formulation is a replicated structured neural network that is trained using mini-batch gradient-based methods;
- a translator module that generates a score and a plurality of sub-scores based on the created replicated semi-additive index data structure, wherein generating the score involves ranking a relative effect of a disparity to a plurality of elements of the created replicated semi-additive index data structure, wherein the ranking comprises ranking relative importance of a decomposed effect of the disparity, wherein the score is indicative of a match status to the at least one machine learning model with the opacity issues;
- and a graphical user interface that renders selected characteristics of the created replicated semi-additive index data structure to produce a rendering that depicts the local and global explainability for the black box effect of the at least one machine learning model with the opacity issues.
A non-transitory computer readable medium having instructions to control one or more processors configured to:
- employ Locally Interpretable Models and Effects based on Supervised Partitioning (LIME-SUP) techniques on a plurality of machine learning models, comprising at least one machine learning model with opacity issues that include a black box effect, to create a replicated semi-additive index data structure that provides local and global explainability for the black box effect,
- wherein the replicator communicates with a library of interpretable machine learning models, wherein the created replicated semi-additive index data structure is a neural network based formulation of an additive index model where a neural network of the neural network based formulation is a replicated structured neural network that is trained using mini-batch gradient-based methods, and wherein the black box effect is a non-visible operation, of the at least one machine learning model with the opacity issues, that lacks explainability;
- and
- generate a score and a plurality of sub-scores based on the created replicated semi-additive index data structure, wherein generating the score involves ranking a relative effect of a disparity to a plurality of elements of the created replicated semi-additive index data structure, wherein the ranking comprises ranking relative importance of a decomposed effect of the disparity, wherein the score is indicative of a match status to the at least one machine learning model with the opacity issues;
- and
- render selected characteristics of the created replicated semi-additive index data structure to produce a rendering that depicts the local and global explainability for the black box effect of the at least one machine learning model with the opacity issues.
3 more elements
Dependencies are inferred from the claim text.