1. Artificial Intelligence: A Modern Approach by Stuart J. Russell and Peter Norvig (2009): This textbook is widely regarded as the most comprehensive exploration of AI available, covering all facets from search algorithms, game playing machines, robotics to natural language processing. It also contains a wealth of code examples for readers interested in learning how to program their own AI applications.
2. The Elements of AI by Reaktor and the University of Helsinki (2018): This book offers an accessible entry point into studying artificial intelligence, machine learning and deep learning practices and provides an overview on various concepts such as convolutional networks, recurrent neural networks, supervised & unsupervised learning among others – without requiring any previous programming experience.
3. Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto (2018): Written by two leading researchers in the field of reinforcement learning this volume presents a unified treatment of machine learning methods drawn from neural networks, control theory, evolutionary computation and other areas – essentially making it one of the best books on reinforcement training available today!
4. Machine Learning Yearning-Technical Strategy for AI Engineers in the Era Of Deep Learning By Andrew Ng (2018): As part of his series on effective machine learning strategies this book looks at scenarios where data sets are limited or non-existent; which can occur when working with sensitive data like healthcare patient info; how to prioritize development efforts for maximum impact; ways for speedier outcomes through using transfer-learning techniques among other topics related specifically to applied deep learning engineering practises .