Abstract: Explainable AI, or XAI, is a rapidly expanding field of research that aims to supply methods for understanding model predictions. We will start by providing a general introduction to the field of explainability, introduce the Alibi library and focus on how it helps you to understand trained models. We will then explore the collection of algorithms provided by Alibi and the types of insight they each provide, looking at a broad range of datasets and models, discussing the pros and cons of each. In particular, we'll look at methods that apply to any model. The focus will be on application to real-world datasets to show the practitioner that XAI can justify, explore and enhance their use of ML.
Background Knowledge:
Basic familiarity with python is desirable
Bio: Alex Athorne is a Research Engineer at Seldon, where he works on open-source libraries for explainability and drift detection. He studied mathematics at Warwick and went on to do a PhD at Imperial College London in dynamical systems. He's passionate about open-source development and writing about his experiences in ML.
