LIME

• @ribeiroWhyShouldTrust2016
• novel model-agnostic modular and extensible explanation technique that explains the predictions of any classifier in an interpretable and faithful manner
• learning an interpretable model locally around the prediction
• SP-LIME
• method to explain models by selecting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem and providing a global view of the model to users
• flexibility of these methods by explaining different models for text (e.g random forests) and image classification (e.g neural networks)
• usefulness of explanations is shown via novel experiments, both simulated and with human subjects
•