Explainable AI - How to build a trustworthy model

"AI-based systems are disrupting almost every industry – healthcare, finances, education, retail, media, marketing, social, economy, HR system, etc, etc., and helping us to make crucial decisions that are impacting millions of lives. Hence it is important to understand how these decisions are made by the AI system. Can we trust the Machine Learning, Deep Learning models, and their training algorithms? The entire process involves a group of people. The bias can be introduced at every level of the entire cycle. How can we examine the fairness of the decision and predictions made by the AI / ML system? We can build an intelligent solution to detect bias in dataset, model development, and each stage of the Model Pipeline. In my session, I will talk about how to build a trustworthy machine learning model which will explain the Model prediction visually."