Ai+ Training

Model ethics, interpretability, and trust will be seminal issues in data science in the coming decade. This technical talk discusses traditional and modern approaches for interpreting black box models. Additionally, we will review cutting edge research coming out of academia and industry. This new research reveals holes in traditional approaches like SHAP and LIME when applied to some deep net architectures. It also introduces a new approach to explainable modeling which optimizes for a balance of interpretability and accuracy rather than viewing interpretability as only a post-modeling exercise. We provide step-by-step guides that practitioners can use in their work to navigate this interesting space. We review code examples of modern interpretability techniques and provide notebooks for attendees to download.