Responsibility: An Example-based Explainable AI approach via Training Process Inspection

no code implementations • 7 Sep 2022 • Faraz Khadivpour, Arghasree Banerjee, Matthew Guzdial

Explainable Artificial Intelligence (XAI) methods are intended to help human users better understand the decision making of an AI agent.

Decision Making Explainable artificial intelligence +2

Explainability via Responsibility

no code implementations • 4 Oct 2020 • Faraz Khadivpour, Matthew Guzdial

We evaluate this approach by approximating its ability to provide human users with the explanations of AI agent's actions and helping them to more efficiently cooperate with the AI agent.

BIG-bench Machine Learning Explainable artificial intelligence