Deep Learning

Deep Learning: Foundations and Concepts aims to offer both newcomers to machine learning and those already experienced in the field a comprehensive grasp of fundamental ideas underpinning deep learning. Covering key concepts related to contemporary deep learning architectures and techniques, this essential book will equip readers with a robust foundation for potential future specialization. The field of deep learning is undergoing rapid evolution. Rather than summarizing the latest research developments, Bishop distills the key ideas in order to ensure that the foundations and concepts presented in this book will endure the test of time. For enhanced accessibility, the book is organized into numerous bite-sized chapters, each exploring a distinct topic. The narrative follows a linear progression, with each chapter building upon content from its predecessors. This structure lends itself effectively to teaching a two-semester undergraduate or postgraduate machine learning course, while remaining equally relevant to those engaged in active research or in self-study.To fully grasp machine learning, a certain level of mathematical understanding is required. The book provides a self-contained introduction to probability theory, and includes appendices summarizing useful results in linear algebra, calculus of variations, and Lagrange multipliers. However, the focus of the book is on conveying a clear understanding of ideas rather than mathematical rigor, with emphasis on real-world practical value of techniques rather than abstract theory. Complex concepts are presented from multiple perspectives including textual descriptions, diagrams, mathematical formulae, and pseudo-code to cater to readers from diverse backgrounds.This book can be viewed as a successor to Neural Networks for Pattern Recognition (Bishop, 1995a) which provided the first comprehensive treatment of neural networks from a statistical perspective. It can be considered as a companion volume to Pattern Recognition and Machine Learning (Bishop, 2006) which covered a broader range of topics in machine learning but predates the deep learning revolution.

Chris Bishop is a Technical Fellow at Microsoft and is the Director of Microsoft Research AI4Science. He is a Fellow of Darwin College, Cambridge, a Fellow of the Royal Academy of Engineering, a Fellow of the Royal Society of Edinburgh, and a Fellow of the Royal Society of London. He is a keen advocate of public engagement in science, and in 2008 he delivered the prestigious Royal Institution Christmas Lectures, established in 1825 by Michael Faraday, and broadcast on prime-time national television. Chris was a founding member of the UK AI Council and was also appointed to the Prime Minister’s Council for Science and Technology.Hugh Bishop is an Applied Scientist at Wayve, an end-to-end deep learning based autonomous driving company in London, where he designs and trains deep neural networks. Before working at Wayve, he completed his MPhil in Machine Learning and Machine Intelligence in the engineering department at Cambridge University. Hugh also holds an MEng in Computer Science from the University of Durham, where he focused his projects on deep learning. During his studies, he also worked as an intern at FiveAI, another autonomous driving company in the UK, and as a Research Assistant, producing educational interactive iPython notebooks for machine learning courses at Cambridge University.