Vorwort
Up-to-date guide to deep learning with unique content, rigorous math, unified notation, comprehensive algorithms, and high-quality figures.

Autorentext
Iddo Drori is a faculty member and associate professor at Boston University, a lecturer at MIT, and adjunct associate professor at Columbia University. He was a visiting associate professor at Cornell University in operations research and information engineering, and research scientist and adjunct professor at NYU Center for Data Science, Courant Institute, and NYU Tandon. He holds a PhD in computer science and was a postdoctoral research fellow at Stanford University in statistics. He also holds an MBA in organizational behavior and entrepreneurship and has a decade of industry research and leadership experience. His main research is in machine learning, AI, and computer vision, with 70 publications and over 5,100 citations, and he has taught over 35 courses in computer science. He has won multiple competitions in computer vision conferences and received multiple best paper awards in machine learning conferences.

Klappentext

This accessible book explains the law and policy of taxation to support economic prosperity and social cohesion in a global, digital era. Legal scholars, practitioners, policy makers, administrators, economists, and social historians will benefit from its wide-ranging exploration of the history and future of taxation to finance government.

Zusammenfassung
This up-to-date guide to deep learning is intended for students in computer science, electrical engineering, data science, statistics, and OR as well as researchers in academia and industry. State-of-the-art topics include transformers, GNNs, VAEs, and deep RL. Complementary code and hundreds of exercises with solutions are provided on the website.

Inhalt

Preface; Notation; Part I. Foundations: 1. Introduction; 2. Forward and backpropagation; 3. Optimization; 4. Regularization; Part II. Architectures: 5. Convolutional neural networks; 6. Sequence models; 7. Graph neural networks; 8. Transformers; Part III. Generative Models: 9. Generative adversarial networks; 10. Variational autoencoders; Part IV. Reinforcement Learning: 11. Reinforcement learning; 12. Deep reinforcement learning; Part V. Applications: 13. Applications; Appendices; References; Index.