Artificial Intelligence and Causal Inference
本书综述深度神经网络与因果推断的交叉领域，介绍变分自编码器、生成对抗网络等深度学习模型，以及Pearl的do-演算、中介分析等因果方法，并探讨两者结合的主题如强化学习和反事实推理。适合想从数学层面理解前沿方法的读者。
This book presents a theoretical overview of recent developments at the interface between deep neural networks and causal inference (although the title mentions Artificial Intelligence, the methods discussed are exclusively neural networks). Chapters 1–4 introduce deep learning models, including variational autoencoders, generative adversarial networks and neural networks as Gaussian processes. Chapter 5 then discusses causal models, including Pearl’s do-calculus, mediation analysis, confounding, instrumental variables and how these can be integrated with neural networks. The remaining chapters discuss various topics that combine both deep neural networks and causal inference, such as reinforcement learning and counterfactual reasoning. Both deep learning and causal inference are fast-moving fields, and the author covers the latest topics and methods well. The book has a high ratio of equations to text, and even more technical material is contained in appendices at the end of each chapter. No worked examples with data are provided to illustrate how the methods should be implemented; however, at the end of each chapter links to software packages and code (primarily GitHub repositories) developed by others are provided. Although readers will gain a mathematical understanding of the latest methods, they will have to look elsewhere for examples of how to analyse and interpret the results.