Artificial Intelligence Engines. A Tutorial Introduction to the Mathematics of Deep Learning Żory

This book is a comprehensive guide to the mathematics behind artificial intelligence engines, taking readers from foundational concepts to advanced applications. It begins with an introduction to artificial neural networks, exploring topics like perceptrons, linear associative networks, and gradient descent. Practical examples accompany each chapter, making complex mathematical principles accessible, even for those with limited prior knowledge.The book's detailed structure covers key algorithms like backpropagation, Hopfield networks, and Boltzmann machines, advancing to deep restricted Boltzmann machines, variational autoencoders, and convolutional neural networks. Modern topics such as generative adversarial networks, reinforcement learning, and capsule networks are explored in depth. Each section connects theory to real-world AI applications, helping readers understand how these techniques are used in practice.Ideal for students, researchers, and AI enthusiasts, the book balances theoretical depth with practical insights. Basic mathematical knowledge or foundation is recommended, allowing readers to fully engage with the content. This book serves as an accessible yet thorough resource for anyone eager to dive deeper into artificial intelligence and machine learning. Spis treści: 1. Artificial Neural Networks2. Linear Associative Networks3. Perceptrons4. The Backpropagation Algorithm5. Hopfield Nets6. Boltzmann Machines7. DeepRBMs8. Variational Autoencoders9. Deep Backprop Networks10. Reinforcement Learning11. The Emperor's New AI? O autorze: James V Stone is a distinguished academic and author specializing in computational neuroscience, artificial intelligence, and information theory. He earned a BSc in Psychology and Pharmacology from Manchester University, an MSc in Knowledge-Based Systems, and a DPhil in Computer Vision from Sussex University. A former Wellcome Mathematical Biology Research Fellow and Associate Professor at the University of Sheffield, James has investigated topics like brain evolution, quantum mechanics, and the Baldwin effect. Since 2017, he has focused on making complex scientific ideas accessible through compelling writing.