5. Deep Learning on Graphs by Yao Ma, Jiliang Tang
Deep Learning on Graphs overs comprehensive contents in developing deep learning techniques for graph structured data with a specific focus on Graph Neural Networks (GNNs).
The foundation of the GNN models are introduced in detail including the two main building operations: graph filtering and pooling operations. We then discuss the robustness and scalability of the GNNs, which are extremely important for utilizing GNNs for real-world applications. To enable deep learning techniques to advance more graph tasks under wider settings, the authors introduce numerous deep graph models beyond GNNs. They also present the most representative applications of GNNs in different areas such as Natural Language Processing, Computer Vision, Data Mining and Healthcare. The book is also self-contained, the authors include chapters for introducing some basics on graphs and also on deep learning. The book concludes with recent advances of GNNs in both methods and applications.
6. Deep Reinforcement Learning by Aske Plaat
Deep reinforcement learning is the combination of deep learning and reinforcement learning.
The author describes the foundations, the algorithms and the applications of deep reinforcement learning. He covers the established model-free and model-based methods that form the basis of the eld. Developments go quickly, and Aske also covers more advanced topics: deep multi-agent reinforcement learning, deep hierarchical reinforcement learning, and deep meta learning.
7. Understanding Deep Learning by Simon J.D. Prince
This book is primarily about the ideas that underlie deep learning.
The first part of the book introduces deep learning models and discusses how to train them, measure their performance, and improve this performance. The next part considers architectures that are specialized to images, text, and graph data. These chapters require only introductory linear algebra, calculus, and probability and should be accessible to any second-year undergraduate in a quantitative
discipline.
Subsequent parts of the book tackle generative models and reinforcement
learning. These chapters require more knowledge of probability and calculus and target
more advanced students.
8. Multimodal Deep Learning by various authors
This book is the result of an experiment in university teaching.
Multimodal learning is a type of deep learning that integrates and processes multiple types of data, referred to as modalities, such as text, audio, images, or video.
Pages in this article:
Page 1: The Little Book of Deep Learning and more books
Page 2: Deep Learning on Graphs and more books