Deep Learning

Andrew Glassner is a research scientist specializing in computer graphics and deep learning. He is currently a Senior Research Scientist at Weta Digital, where he works on integrating deep learning with the production of world-class visual effects for films and television. He has previously worked as a researcher at labs such as the IBM Watson Lab, Xerox PARC, and Microsoft Research. He was Editor in Chief of ACM TOG, the premier research journal in graphics, and Technical Papers Chair for SIGGRAPH, the premier conference in graphics. He's written or edited a dozen technical books on computer graphics, ranging from the textbook Principles of Digital Image Synthesis to the popular Graphics Gems series, offering practical algorithms for working programmers. Glassner has a PhD in Computer Science from UNC-Chapel Hill.

"Andrew is famous for his ability to teach complex topics that blend mathematics and algorithms, and this work I think is his best yet."—Peter Shirley, Distinguished Research Engineer, Nvidia“I would recommend that anyone entering this area, or even already familiar with the subject, read it cover-to-cover to firmly ground their understanding.“—Richard Szeliski, author of Computer Vision: Algorithms and Applications"This is a comprehensive—yet easy to understand—book about complex concepts and algorithms. Andrew Glassner demonstrates that visualizing concepts as graphs is a tremendous benefit to easy cognition."—Thomas Frisendal, author of Graph Data Modeling for NoSQL and SQL"An absolutely amazing book in the field of Machine Learning. Lots of colored visuals make the concepts very easy to understand."—Nabeel حسن, @nabeelhasan25"This is the best technical book I've ever read. I'm essentially speechless. Thank you, @AndrewGlassner!"—Maciej Chmielarz, @MaciejChmielarz, Software Developer

• Part I: Foundational Ideas1. An Overview of Machine Learning Techniques2. Essential Statistical Ideas3. Probability4. Bayes’ Rule5. Curves and Surfaces6. Information TheoryPart II: Basic Machine Learning7. Classification8. Training and Testing9. Overfitting and Underfitting10. Data Preparation11. Classifiers12. EnsemblesPart III: Deep Learning Basics13. Neural Networks14. Backpropagation15. OptimizersPart IV: Beyond the Basics16. Convolutional Neural Networks17. Convnets in Practice18. Recurrent Neural Networks19. Autoencoders20. Reinforcement Learning21. Generative Adversarial Networks22. Creative ApplicationsIndex