CPC G06V 10/763 (2022.01) [G06F 18/23213 (2023.01); G06N 3/04 (2013.01); G06N 3/084 (2013.01)] | 24 Claims |
17. A computing apparatus comprising:
a processor; and
a memory storing instructions that, when executed by the processor, configure the processor to:
determine local attributions for a set of samples, and each local attribution includes a rank and a weight of an association between a particular feature and a particular prediction predicted by a neural network;
normalize each local attribution;
compare pairs of local attributions, and assigning a rank distance thereto proportional to a degree of ranking differences between the pair of normalized local attributions;
apply a clustering algorithm to generate clusters of the local attributions, wherein the clustering algorithm utilizes the ranking distances for each pair of normalized local attributions to assign each local attribution to one of one or more clusters, and each cluster having a medoid;
generate global attributions, wherein each global attribution corresponds to one of the medoids of one of the clusters; and
determine a bias in the neural network, one or more features to include in the neural network, or a combination thereof based on the global attributions.
|