Explainable AI

The inner workings of many deep learning systems are complicated if not impossible for the human mind to comprehend. Explainable Artificial Intelligence (XAI) aims to provide AI experts with transparency into these systems. In this course youll describe what Explainable AI is how to use it and the data structures behind XAIs preferred algorithms. Next youll explore the interpretability problem and todays state-of-the-art solutions to it. Youll identify XAI regulations define the "right to explanation" and illustrate real-world examples where this has been applicable. Youll move on to recognize both the Counterfactual and Axiomatic methods distinguishing their pros and cons. Youll investigate the intelligible models method along with the concepts of monotonicity and rationalization. Finally youll learn how to use a Generative Adversarial Network.