"Deep Generative Modeling": Introductory Examples (github.com)

A new book titled "Deep Generative Modeling" has been released, marking the first comprehensive guide to the myriad of techniques underpinning Generative AI. Authored by Jakub M. Tomczak, the book extensively covers major classes of deep generative models, including mixture models, Probabilistic Circuits, GANs, and Large Language Models. Designed for readers with a foundational understanding of mathematics and programming, it incorporates real-world examples and code snippets using popular libraries like PyTorch and Jupyter notebooks. The emphasis on engagement with simplistic examples allows novice users to easily grasp and experiment with deep generative modeling techniques. This publication is significant for the AI/ML community as it demystifies complex generative processes, thereby fostering a broader understanding and accessibility to these powerful tools. By simplifying advanced concepts, the book encourages both new learners and seasoned practitioners to explore and innovate within the realm of deep generative modeling. The provided Jupyter notebooks facilitate practical experimentation and application, further enhancing educational outreach in diverse fields such as computer science, engineering, and bioinformatics.