Explainability is emerging as a critical aspect of AI and in particular Deep Learning Models. It is useful for compliance, decision maker acceptance and also for improved continuous training and stabilization of the model. We present a mathematically rigorous definition of explainability and how it is applied to several vision tasks in the healthcare and video analytics domains. A basic need of commercial AI systems is to be able to learn new special cases, which did not exist in the training dataset, from very few new samples. This too is accomplished using our formalism.

Session Overview

  • 01

    Practical, Rigorous Explainability in AI

    • Abstract & Bio

    • Practical, Rigorous Explainability in AI


Start your 14-days trial. Cancel anytime.