Source: ZHUAN ZHI
This article introduces a book and suggests a 5-minute read.
After reading this book, you will understand the mathematical foundations and concepts of deep learning, and be able to build new deep learning applications using the demonstrated prototypes.
This book is built on the foundation of the first edition, updating chapters and the latest code implementations to align with TensorFlow 2.0.
https://link.springer.com/book/10.1007/978-1-4842-8931-0
TensorFlow 2.0 Pro Deep Learning with TensorFlow 2.0 starts with the mathematical and core technical foundations of deep learning. Next, you will learn about convolutional neural networks, including new convolution methods such as dilated convolutions, depthwise separable convolutions, and their implementations. Then, you will understand natural language processing in advanced network architectures (such as transformers), as well as various attention mechanisms related to natural language processing and general neural networks. As you delve deeper, you will explore unsupervised learning frameworks that reflect the current state of deep learning methods, such as autoencoders and variational autoencoders. The final chapter covers advanced topics of generative adversarial networks and their variants, such as cycle-consistent GANs and graph neural network techniques, such as graph attention networks and GraphSAGE.
After reading this book, you will understand the mathematical foundations and concepts of deep learning, and be able to build new deep learning applications using the demonstrated prototypes.
-
Understand full-stack deep learning using TensorFlow 2.0
-
Understand the mathematical foundations of deep learning
-
Deploy complex deep learning solutions in production using TensorFlow 2.0
-
Understand generative adversarial networks, graph attention networks, and GraphSAGE
