Scientists and practitioners increasingly rely on machine learning to model data and draw conclusions. Compared to statistical modeling approaches, machine learning makes fewer explicit assumptions about data structures, such as linearity. However, their model parameters usually cannot be easily related to the data generating process. To learn about the modeled relationships, partial dependence (PD) plots and permutation feature importance (PFI) are often used as interpretation methods. However, PD and PFI lack a theory that relates them to the data generating process. We formalize PD and PFI as statistical estimators of ground truth estimands rooted in the data generating process. We show that PD and PFI estimates deviate from this ground truth due to statistical biases, model variance and Monte Carlo approximation errors. To account for model variance in PD and PFI estimation, we propose the learner-PD and the learner-PFI based on model refits, and propose corrected variance and confidence interval estimators.

Over the past two years, we've seen the release of many books that provide deep insights about the fundamental concepts, technical process, and applications of artificial intelligence. This list highlights books authored by renowned computer scientists and practitioners who are entrenched in the AI industry. No matter you are a researcher, an engineer, or a business professional in the AI/ML domain, your are bound to find a few interesting books to add to your reading list this year! In this book, professors at New York University Gary Marcus and Ernest Davis explain the technological and theoretical gap between creating successful AI which is constrained to a fixed set of rules (or a fixed environment), and creating successful AI which can effectively interact with the complexities and intricacies of an open world. This book is for researchers and entrepreneurs who want to make practical predictions on the immediate future of AI. Gary Marcus is a Professor of Psychology and Neural Science and CEO of Robust.AI, and Ernest Davis is a Professor of Computer Science.

Christoph Molnar is one of the main people to know in the space of interpretable ML. In 2018 he released the first version of his incredible online book, interpretable machine learning. Interpretability is often a deciding factor when a machine learning (ML) model is used in a product, a decision process, or in research. Interpretability methods can be used to discover knowledge, to debug or justify the model and its predictions, and to control and improve the model, reason about potential bias in models as well as increase the social acceptance of models. But Interpretability methods can also be quite esoteric, add an additional layer of complexity and potential pitfalls and requires expert knowledge to understand.

Preface Machine learning has a huge potential to improve products, processes and research. But machines usually don't give an explanation for their predictions, which hurts trust and creates a barrier for the adoption of machine learning. This book is about making machine learning models and their decisions interpretable. Machine learning models are already used to choose the best advertisement for you, it filters out spam from your emails and it even assesses risk in the judicial system which ultimately can have consequences for your freedom. Can everyone trust the learned model?