Semi-local model importance in feature space
AssigneeThe Toronto-Dominion Bank
InventorsKin Kwan Leung, Saba Zuberi, Maksims Volkovs, Jianing Sun
Life of this patent
Estimating the term…
Loading patent…
AssigneeThe Toronto-Dominion Bank
InventorsKin Kwan Leung, Saba Zuberi, Maksims Volkovs, Jianing Sun
Estimating the term…
To provide explanations for black box computer models, data samples are processed by the model to determine related feature attributions for each data sample, describing the extent to which feature values affect the model predictions for that data sample. A group of data samples is selected to be explained and the group is clustered into subgroups based on the feature attributions of the data samples. Because explanations related to feature attributions can be difficult to interpret or relate to input features, each of the subgroups is then described in the feature space, enabling ready interpretation of the groups at a semi-local level.
A system comprising:
A method, comprising:
A non-transitory computer-readable medium comprising instructions that, when executed by a processor, cause the processor to:
Dependencies are inferred from the claim text.