Causal inference

In the advanced computing age of the twenty-first century, Artificial Intelligence (AI) is wellaccepted idea by professionals in areas in which human efforts are severely limited because of physical or thought constraints. Other synonymous names to the core ideas of AI are machine learning, neural networks, expert system, mathematical optimization, deep learning, etc. However, the goals are to comprehend and utilize reasoning, planning, and execution of intelligence. The earliest mention of AI was by a British logician Alan Mathison Turing as he was exploring the use of limitless memory of the computer to perform supervised or unsupervised machine learning. The AI is a mix of hardware engineering, image processing, statistics, computer science, psychology, linguistics, and philosophy. The book is a byproduct of the author’s extensive research work on big data analysis. There are eight extremely well-written chapters covering a range of topics, including three types of neural networks, basic foundations of deep learning, Gaussian process, deep generative models, matrix normal distribution, auto encoders, adversarial networks, functional adaptive models, structural equations, graph-theoretic approaches, mediation analysis, confounding, bivariate and multivariate time series techniques versus causalities including Granger causality, counterfactual inference, survival inference, Markovian versus dynamic reinforcement learning, approximating functions to ease interpretations among others. The readers need to have an excellent background in calculus, differential equations, probability, control theory, and statistics. The references are exhaustive and up to date. Every chapter of the book utilizes software to apply, compute, and interpret the results of tensor calculus, entropy, Pontryagin’s maximum principle and calculus of variations. The book is suitable for use in a graduate-level course on AI. The exercises are challenging but their answers are provided in the end of the book. Not all contents are understandable by the statistics community or commonly useful in the practice of statistics. I enjoyed reading this book. I recommend this book to engineering, data science, predictive business, statistics and computing professionals.