Register for 16 December Webinar: "Is explainable AI really explainable to the end user?"
December 7, 2021
Despite the recent impetus in the field of explainable AI models, the majority of the proposed techniques are extremely limited in terms of their practical utility and the nature of explanations they provide. Given the inherent risks associated with incorrect explanations, some researchers have proposed to stop explaining opaque ML models entirely and instead rely solely on interpretable ML. This raises an important question about the end goal of explainable AI: "Is it simply assisting the AI developer who is trying to debug an ML model?" For explainable AI to aid in deployment, the objective must be to provide explanations to the end user of the AI system, who is most likely a domain expert such as a doctor or engineer.
Join us for the TCS Research webinar organized with ACM India as AI experts from TCS Research and academia discuss the efficacy of explainable AI models. The webinar will consist of a talk on "Two Understability Axioms for ML with Humans-in-the-Loop," followed by a Fireside Chat on "The Role of Domain Knowledge in Modern Understandable AI," where speakers will highlight the ways of reducing the gap between explainable AI models and the domain expert, or in other words, how the two can speak the same language.
Date: 16 December 2021
Time: 6 PM IST