A Survey of the Various Methodologies Towards making Artificial Intelligence More Explainable

Abstract

Machines are being increasingly used in decision-making processes, resulting in the realization that decisions need explanations. Unfortunately, an increasing number of these deployed models are of a 'black-box' nature where the reasoning behind the decisions is unknown. Hence, there is a need for clarity behind the reasoning of these decisions. As humans, we would want these decisions to be presented to us in an explainable manner. However, explanations alone are insufficient. They do not necessarily tell us how to achieve an outcome but merely tell us what achieves the given outcome. For this reason, my research focuses on explainability/interpretability and how it extends to counterfactual thinking.