This accessible and engaging textbook presents a concise introduction to the exciting field of artificial intelligence (AI). The broad-ranging discussion covers the key subdisciplines within the field, describing practical algorithms and concrete applications in the areas of agents, logic, search, reasoning under uncertainty, machine learning, neural networks, and reinforcement learning. Fully revised and updated, this much-anticipated second edition also includes new material on deep learning.

Dr. Reinhard Klette, Fellow of the Royal Society of New Zealand, is a Professor at the Auckland University of Technology (AUT). His numerous publications include the books "Computer Vision for Driver Assistance" (co-authored by Mahdi Rezaei), "Multi-target Tracking" (co-authored by Junli Tao), "Concise Computer Vision", "Euclidean Shortest Paths" (co-authored by Fajie Li), "Panoramic Imaging" (co-authored by Fay Huang and Karsten Scheibe), "Digital Geometry" (co-authored by the late Azriel Rosenfeld), "Computer Vision - Three-Dimensional Data from Images" (co-authored by Karsten Schluens and Andreas Koschan), "The Handbook of Image Processing Operators" (co-authored by the late Piero Zamperoni), and "Fast Algorithms and their Implementation on Specialized Parallel Computers" (co-authored by Jozef Miklosko, Marian Vajtersic, and Imre Vrto)

Topics and features: introduces dynamic programming and other fundamental algorithm design techniques, and investigates a wide selection of graph algorithms; compatible with the IOI Syllabus, yet also covering more advanced topics, such as maximum flows, Nim theory, and suffix structures; surveys specialized algorithms for trees, and discusses the mathematical topics that are relevant in competitive programming; reviews the features of the C programming language, and describes how to create efficient algorithms that can quickly process large data sets; discusses sorting algorithms and binary search, and examines a selection of data structures of the C standard library; covers such advanced algorithm design topics as bit-parallelism and amortized analysis, and presents a focus on efficiently processing array range queries; describes a selection of more advanced topics, including square-root algorithms and dynamic programming optimization.

I'm a programmer with no great mathematical background (2nd year university maths and stats, decades old and mostly forgotten) trying to teach myself about machine learning, and I found this book to be at exactly the right level for me. It's strongly oriented towards classifiers of one sort and another, and makes no claims to cover neural nets, genetic algorithms, genetic programming - but what it does cover it covers exceptionally clearly. I'd give it six stars out of five if it covered all aspects of machine learning, but I guess I can't have everything. In terms of writing style and comprehensibility this is probably one of the best textbooks I have ever read. I wish that it covered much much more, but what it does do it does remarkably well.