Abstract:
The vast diversity of internal designs of black-box AI systems and their nuanced zones of safe functionality make it difficult for a layperson to use them without unintended side effects. The focus of my dissertation is to develop algorithms and requirements of interpretability that would enable a user to assess and understand the limits of an AI system's safe operability. We develop an assessment module that lets an AI system execute high-level instruction sequences in simulators and answer the user queries about its execution of sequences of actions. Our results show that such a primitive query-response capability is sufficient to efficiently derive a user-interpretable model of the system in stationary, fully observable, and deterministic settings.
