Accumulated local effects
Inspect accumulated local changes in predictions across a tabular feature.
Testing methods
11Deletion and insertion AUC
Measure prediction changes as attributed image regions are removed or inserted.
Energy pointing game
Measure how much attribution energy falls inside a reference region.
Grad-CAM
Use model feature maps to attribute an image prediction to regions of the input.
Integrated Gradients
Attribute an image prediction by integrating gradients from a reference input.
LIME
Approximate a tabular prediction locally with an interpretable model.
Occlusion
Hide image regions in turn and inspect the change in the model's prediction.
Partial dependence
Inspect average model predictions as a tabular feature changes.
Permutation importance
Shuffle tabular features and measure the change in model performance.
Pointing game
Check whether the strongest attribution falls inside a reference region.
Saliency
Use input gradients to inspect pixel sensitivity for an image prediction.
1–11 of 11 results