2024-07-22
한어Русский языкEnglishFrançaisIndonesianSanskrit日本語DeutschPortuguêsΕλληνικάespañolItalianoSuomalainenLatina
This is probably one of the most comprehensive and up-to-date overviews of deep learning available today.
The explosively popular field of deep learning has recently seen new popular learning materials.
Recently, the Chinese version of MIT Press's new book "Understanding Deep Learning" was released.
This book is divided into 21 chapters, covering many key concepts in the field of deep learning, including basic construction, Transformer architecture, graph neural network GNN, reinforcement learning RL, diffusion model, etc. It is of great value to both beginners and experienced developers.
GitHub 链接：https://github.com/careywyr/UnderstandingDeepLearning-ZH-CN
Original link of the book: https://udlbook.github.io/udlbook/
At present, the English electronic version of the book has been downloaded 344,000 times.
The physical version of the book was officially released in December last year. The book has 541 pages, but its electronic version has been continuously updated. Currently on the website, the author also provides 68 Python notebook exercises to help readers deepen their understanding through programming practice.
This book hopes to introduce the basic ideas of deep learning to people in an accurate and easy-to-understand way, aiming to help beginners understand the principles behind deep learning. For readers who want to understand the content of this book in depth, only undergraduate-level mathematical knowledge is required to read it.
Specifically, the book introduces deep learning models in the early parts and discusses how to train, evaluate, and improve these models. In the following parts, the author will take us to examine architectures specifically for image, text, and graph data. Subsequent chapters explore generative models and reinforcement learning. The penultimate chapter explores these and other aspects that are not yet fully understood. The last chapter discusses AI ethics.
Table of contents
Chapter 1 - Introduction
Chapter 2 - Supervised learning
Chapter 3 - Shallow neural networks
Chapter 4 - Deep neural networks
Chapter 5 - Loss functions
Chapter 6 - Fitting models
Chapter 7 - Gradients and initialization
Chapter 8 - Measuring performance
Chapter 9 - Regularization
Chapter 10 - Convolutional networks
Chapter 11 - Residual networks
Chapter 12 - Transformers
Chapter 13 - Graph neural networks
Chapter 14 - Unsupervised learning
Chapter 15 - Generative adversarial networks
Chapter 16 - Normalizing flows
Chapter 17 - Variational autoencoders
Chapter 18 - Diffusion models
Chapter 19 - Deep reinforcement learning
Chapter 20- Why does deep learning work? Why does deep learning work?
Chapter 21 - Deep learning and ethics
about the author
The author of "A Deeper Understanding of Deep Learning" is Simon JD Prince, a professor of computer science at the University of Bath in the UK, who focuses on computer vision and computer graphics.
According to his LinkedIn profile, Simon JD Prince has been working in computer science and AI research at research institutions for more than a decade, including serving as chief scientist at software development company Anthropics Technology for seven years. In 2022, he joined the University of Bath as an honorary professor.
Simon JD Prince has published more than 50 papers in top conferences (CVPR, ICCV, SIGGRAPH, etc.). He is also the author of Computer Vision: Models, Learning, and Reasoning.
https://x.com/tuturetom/status/1814689613304508777
Collect and organize the latest news information and make it available for free for everyone to read
