Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play 1st Edition by David Foster (PDF)

Description

Generative modeling is one of the hottest topics in AI. It’s now possible to teach a machine to excel at human endeavors such as painting, writing, and composing music. With this practical book, machine-learning engineers and data scientists will discover how to re-create some of the most impressive examples of generative deep learning models, such as variational autoencoders,generative adversarial networks (GANs), encoder-decoder models, and world models.Author David Foster demonstrates the inner workings of each technique, starting with the basics of deep learning before advancing to some of the most cutting-edge algorithms in the field. Through tips and tricks, you’ll understand how to make your models learn more efficiently and become more creative.Discover how variational autoencoders can change facial expressions in photosBuild practical GAN examples from scratch, including CycleGAN for style transfer and MuseGAN for music generationCreate recurrent generative models for text generation and learn how to improve the models using attentionUnderstand how generative models can help agents to accomplish tasks within a reinforcement learning settingExplore the architecture of the Transformer (BERT, GPT-2) and image generation models such as ProGAN and StyleGAN

User’s Reviews

Editorial Reviews: About the Author David Foster is the co-founder of Applied Data Science, a data science consultancy delivering bespoke solutions for clients. He holds an MA in Mathematics from Trinity College, Cambridge, UK and an MSc in Operational Research from the University of Warwick.David has won several international machine learning competitions, including the Innocentive Predicting Product Purchase challenge and was awarded first prize for a visualisation that enables a pharmaceutical company in the US to optimize site selection for clinical trials.He is an active participant in the online data science community and has authored several successful blog posts on deep reinforcement learning including ‘How To Build Your Own AlphaZero AI’.

Reviews from Amazon users which were colected at the time this book was published on the website:

⭐Cover basic but important technique of generative model and deep learning such as VAE and different type of GAN in understandable manner.Great explanation of key deep learning tools such as convolution and different kinds of loss function.Would appreciate if the codes comes with pytorch version (although I did find one repo on GitHub that cover this book chapter in pytorch)Looking forward to an updated version that talks about newer technique such as diffusion model

⭐I’m a ML engineer. I know the ropes. I’ve spent hours surfing the web for explanations and sample implementations of deep learning and GAN methodology. You might have too. You might be wondering, “why would I need this book when I have access to Medium?” And that’s a good question. I can answer that for you.If you’ve been around for a while, you might know that Medium content can be repetitive, unoriginal, full of too much filler, full of code that can’t be re-used, or in the habit of explaining mathematics/probability poorly. The difference between this book and Medium is that this book doesn’t do that. It’s got good introductions to each popular dataset, contains useful code, is highly readable and refreshing, and uses equations sparingly and effectively, without dumbing down the content too much. I can skim the content easily. It’s top notch, contains a lot of fresh developments like World Models (Ch 8), and seems like an essential book for my ML library.My only critique is that at times, the book seemed to read like a children’s bedtime story. Telling stories is an excellent way to explain concepts, but I don’t know if I need David Foster renaming GAN discriminators and generators “Di and Gene”, with an introduction on “taking photographs of ganimals” to understand what a GAN is. That’s not to say this book does the story bit poorly. If you’re new to all this, it may be really useful for you. It was just a bit off-putting for me.Regardless, I highly recommend it to anyone that has familiarity with basic stats notation and is comfortable with Python3.

⭐The book starts great. Fantastic examples. It appeals to the reader’s intuition and imagination. I loved the beginning and it was very easy working side by side with Jupyter Notebook. The examples are easy to follow and the code is pure Python with Keras. At that point I was going to give the book five stars. However, I was stuck at Autoencoders when the author suddenly started using his own code shortcuts, which was completely unexpected. It took me a while to figure it out that the code was no longer Keras but the functions and objects developed by the author, and imported from the local python files. The book does not explain any of this and the code becomes very obscure. The author’s “models” and “utilities” were clearly meant to simplify development of complex neural networks by the reader. Unfortunately, the code is no longer intelligible as it hides the true Keras APIs. These shortcuts are not really necessary and the code they replace would not add much to the size of the book. In those circumstances, if you move away from the book and the author’s Github repository, you will no longer be able to reproduce the models and their tests easily. While it is expected of any practitioner to develop his or her own helper library, this is not suitable for the book which needs simplicity and clarity. In all honesty, the book does not claim to train the reader in Keras at all, however, it uses Keras and asks the reader to install the software, and then explains the basics of model creation with Keras, only to leave it behind. I’d recommend to replace all obscure code with the simplest model creation, which can be found in any Keras example on the web. As the author is quite responsive to the reviews and open for comments, I have increased my rating.

⭐This book is written in a way that is perfect for explaining the difficult concepts. Each chapter covers a new concept, and it begins by explaining it with an analogy. Then it explains it in real terms. Then it explains it with explicit math and example code. Lots of high quality colored graphs and examples are scattered throughout the book.This is honestly one of the best written textbooks I have ever seen.

⭐Paper is super thin and images seem to have printed by a cheap printer in economy mode.I’m not usually picky about these things but it is very noticeable.Content wise is OK, I especially liked the explanation about mode collapse in GANs and justification of WGAN losses and why they work. There are many analogies to explain concepts (VAEs, GANs, etc) and but I find some of them could be better.

⭐This is a great book to explore major ideas behind state-of-the-art generative deep learning techniques. It covers variational autoencoders, encoder-decoder based approaches, GANs, and much more with code examples in book’s github repo. I wish it had additional chapters to dive deeper into more recent models discussed in the final chapter. Hoping to see a follow-up book by the author since he is very good at explaining complex ideas in a clear manner.

⭐This is a good introductory text to generative models and it is easy to read. The author likes to use lead-in story but some of them are too long-winded and I often had to skim several pages quickly to get to the technical stuff.I was particularly interested in learning GANs to create images but disappointed to find that it uses only simple models with toy datasets. For example, there are many freely available online tutorials on DCGAN and CycleGAN; much of the code in the book were also taken from open-sourced Github repo.Therefore, I went to buy a couple more books and found “Image Generation with TensorFlow” to be the best for my need as it covers not only the basics but also state-of-the-art models like StyleGAN and image transformer.

⭐The book is really a good overview of use-cases, has code samples, some overview of the maths and is reasonably up-to-date. I had some knowledge of GANs prior to reading this book but was missing knowledge on actual implementation to get going, this book filled that gap very well and gave a bunch of terms, definitions and references so I could get going and continue on my own after. Top marks.

⭐Very entertaining reading. Print quality could be better, but that’s on Amazon, not on the author I guess…

⭐Explanations are terrible.

⭐Wie so oft lernt man ein Gebiet em leichtesten, wenn es auch Spaß macht. Und in der Hinsicht sind GANs einfach der perfekte Türöffner, um quasi im Vorbeigehen die Handhabung von Basistechniken wie RNN, Convolutional Layers oder Autoencodern zu lernen.Eine sehr gute Ergänzung zu “Hands on Machine Learning” von Aurelien Geron, wo das Thema GAN doch zu knapp behandelt wird, dafür aber die Basics deutlich ausführlicher.Auch der Quellcode, den der Autor mitliefert, ist in weiten Teilen sehr gut durchdacht und gekapselt, so dass sich die jeweiligen Netzwerke auch auf eigene Anforderungen oder andere Daten anpassen lassen. Wobei hier wie allgemein gelegentlich das Problem mit den Tensorflow-Versionen und anderen Abhängigkeiten besteht, wo man manchmal doch Fehler debuggen muss, die offenbar entstehen, weil Code und aktuelle Versionen nicht mehr ganz passen, selbst wenn man auf einer Minor-Version wie 2.4 bleibt. Das liegt aber nicht am Buch oder Herrn Foster.Etwas schade ist, dass die “brandheißen” Themen der Jahre 2018 und folgnde (Transformer, StyleGAN u.v.m.) erst im Anhang quasi als Ausblick nur angerissen werden, ohne die ausführlichen Beispiele wie bei den simplen Varianten. Diese sind zwar zum Lernen viel übersichtlicher, aber man bekommt schnell das Gefühl, dass man sich ja mit Techniken von “damals”, aus der Urzeit von Deep-Learning beschäftigt, die längst von deutlich leistungsfähigeren Nachfolgern abgelöst wurden. Jedoch versteht man die Nachfolger erst, wenn man die Originale hier verstanden hat und teilweise sind natürlich aktuelle Netze nicht mehr so einfach auf heimischer Hardware zu trainieren oder überhaupt nicht quelloffen verfügbar.Ich freue mich auf die zweite Auflage!

⭐

Keywords

Free Download Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play 1st Edition in PDF format
Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play 1st Edition PDF Free Download
Download Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play 1st Edition 2019 PDF Free
Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play 1st Edition 2019 PDF Free Download
Download Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play 1st Edition PDF
Free Download Ebook Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play 1st Edition