Generative Deep Learning: Teaching Machines To Paint, Write, Compose, and Play 2nd Edition

In 2019 I bought, read and thoroughly loved the first edition of this book. One reason I loved that edition was the author’s excellent way of explaining generative adversarial networks (GAN), with humorous and relevant examples. At that point I was a lot more naive about the various deep learning models (ANN, RNN, CNN etc) and for a while I was unable to see where GANs fit in in the grand scheme or evolution of deep learning models.With the explosion in interest in generative AI after the release of ChatGPT-3, I read “Natural Language Processing with Transformers” by Turnstall etc. to get an understanding of the Transformer model. Along the way I read other sources of information on language models such as a paper “Survey of Large Language Models” by Socher etc. That later paper gave an excellent overview of the evolution of language models (statistical language models --> neural language models --> pretrained language models —> large language models). I also saw where language models fit in in the context of ANNs, RNN, CNN etc.When I saw that the author released a second edition of “Generative Deep Learning”, I noticed that the content had changed (ie increased) from the first edition, and I immediately decided to buy the second edition. This second edition has an excellent overview of the evolution of generative models, in fact 6 of them (variational auto encoders (VAE) —> generative adversarial networks (GAN) —> autoregressive models —> normalizing flow models —> energy based models —> diffusion models). I had never heard of some of these models. According to this author the Transformer is an application of generative deep learning models. The author goes on to describe other applications such as music generation and multimodal models.While this book requires one to know Python programming and offers code on GitHub, I was able to skip running the code and still learn a lot about generative deep learning. (I tried to run the code examples but couldn’t get around to it. I wish the author provided easier Jupyter notebooks for running the code).Another aspect of the book that I loved was the author’s description of key concepts like “probabilistic” versus “deterministic”, “discriminative” versus “generative” etc.I highly recommend this book as a great resource for a historical overview of generative deep learning. One should read it before one reads anything on just the transformer or language models.

Amazing book, for me the best thing about it is that there are many well-sourced and working code and data examples which are explained clearly in the text.

Hello fellas, I ordered a generative deep learning book from an another source, but had poor quality as well as poor content. But this book is focused on an important part of generative deep learning also has a good quality of content. Really appreciate that I bought this book.

The book is in very good condition, but it has stick notes in it! I seriously doubt they are from the author....

This is a lovely book. It is readable and explains the principles behind algorithms clearly.

Awesome book and great codebase. A reference for modern AI.

I haven't finished yet, but it's been helpful to implement the examples. So far it's been a great learning resource.

This review is for the Kindle edition. I have the 2nd print edition of the book and it looks like the 3rd edition has some good additions but rushed out. In this day and age of spell-checkers, auto-complete, and now generative AI, it is unacceptable that the electronic version has poor quality.Subscripts and other type settings are skipped in many places making it harder to read equations.For example J = dz 1 dx 1... or det abcd = ad bc. For some reason many kindle books are plagued with some symbol getting substituted with a square []. You have to guess what that symbol was supposed to be. For the price, that shouldn't happen.The irony is this a book about generative AI which is supposed to simplify or at least help in such things. If you can wait, maybe there will be a revised edition.