Generative AI with Python and TensorFlow 2

Create images, text, and music with VAEs, GANs, LSTMs, Transformer models

Joseph Babcock , Raghav Bali 지음

Packt(GCO Science) 2021년 04월 30일 출간

작품소개

책소개

Fun and exciting projects to learn what artificial minds can create

▶Book Description
Machines are excelling at creative human skills such as painting, writing, and composing music. Could you be more creative than generative AI?

In this book, you'll explore the evolution of generative models, from restricted Boltzmann machines and deep belief networks to VAEs and GANs. You'll learn how to implement models yourself in TensorFlow and get to grips with the latest research on deep neural networks.

There's been an explosion in potential use cases for generative models. You'll look at Open AI's news generator, deepfakes, and training deep learning agents to navigate a simulated environment.

Recreate the code that's under the hood and uncover surprising links between text, image, and music generation.

▶What You Will Learn
- -Export the code from GitHub into Google Colab to see how everything works for yourself
-Compose music using LSTM models, simple GANs, and MuseGAN
-Create deepfakes using facial landmarks, autoencoders, and pix2pix GAN
-Learn how attention and transformers have changed NLP
-Build several text generation pipelines based on LSTMs, BERT, and GPT-2
-Implement paired and unpaired style transfer with networks like StyleGAN
-Discover emerging applications of generative AI like folding proteins and creating videos from images

▶Key Features
-Code examples are in TensorFlow 2, which make it easy for PyTorch users to follow along
-Look inside the most famous deep generative models, from GPT to MuseGAN
-Learn to build and adapt your own models in TensorFlow 2.x
-Explore exciting, cutting-edge use cases for deep generative AI

▶Who This Book Is For
This is a book for Python programmers who are keen to create and have some fun using generative models. To make the most out of this book, you should have a basic familiarity with math and statistics for machine learning.

목차

▶TABLE of CONTENTS
-Chapter 1: An Introduction to Generative AI: "Drawing" Data from Models
-Chapter 2: Setting Up a TensorFlow Lab
-Chapter 3: Building Blocks of Deep Neural Networks
-Chapter 4: Teaching Networks to Generate Digits
-Chapter 5: Painting Pictures with Neural Networks Using VAEs
-Chapter 6: Image Generation with GANs
-Chapter 7: Style Transfer with GANs
-Chapter 8: Deepfakes with GANs
-Chapter 9: The Rise of Methods for Text Generation
-Chapter 10: NLP 2.0: Using Transformers to Generate Text
-Chapter 11: Composing Music with Generative Models
-Chapter 12: Play Video Games with Generative AI: GAIL
-Chapter 13: Emerging Applications in Generative AI

책 속으로

▶What this book covers
- Chapter 1, An Introduction to Generative AI: "Drawing" Data from Models, introduces the field of generative AI, from the underlying probability theory to recent examples of applied products of these methods.

- Chapter 2, Setting Up a TensorFlow Lab, describes how to set up a computing environment for developing generative AI models with TensorFlow using open source tools ？ Python, Docker, Kubernetes, and Kubeflow ？ in order to run a scalable code laboratory in the cloud.

- Chapter 3, Building Blocks of Deep Neural Networks, introduces foundational concepts for deep neural networks that will be utilized in the rest of the volume ？ how they were inspired by biological research, what challenges researchers overcame in developing ever larger and more sophisticated models, and the various building blocks of network architectures, optimizers, and regularizers utilized by generative AI examples in the rest of the book.

- Chapter 4, Teaching Networks to Generate Digits, demonstrates how to implement a deep belief network, a breakthrough neural network architecture that achieved state-of-the-art results in classifying images of handwritten digits through a generative AI approach, which teaches the network to generate images before learning to classify them.

- Chapter 5, Painting Pictures with Neural Networks Using VAEs, describes variational autoencoders (VAEs), an advancement from deep belief networks which create sharper images of complex objects through clever use of an objective function grounded in Bayesian statistics. The reader will implement both a basic and advanced VAE which utilizes inverse autoregressive flow (IAF), a recursive transformation that can map random numbers to complex data distributions to create striking synthetic images.

- Chapter 6, Image Generation with GANs, introduces generative adversarial networks, or GANs, as powerful deep learning architectures for generative modeling. Starting with the building blocks of GANs

출판사 서평

▶ Preface
In this book we will explore generative AI, a cutting-edge technology for generating synthetic (yet strikingly realistic) data using advanced machine learning algorithms. Generative models have been intriguing researchers across domains for quite some time now. With recent improvements in the fields of machine learning and more specifically deep learning, generative modeling has seen a tremendous uptick in the number of research works and their applications across different areas. From artwork and music composition to synthetic medical datasets, generative modeling is pushing the boundaries of imagination and intelligence alike. The amount of thought and effort required to understand, implement, and utilize such methods is simply amazing. Some of the newer methods (such as GANs) are very powerful, yet difficult to control, making the overall learning process both exciting and frustrating.

Generative AI with Python and TensorFlow 2 is the result of numerous hours of hard work by us authors and the talented team at Packt Publishing to help you understand this deep, wide, and wild space of generative modeling. The aim of this book is to be a kaleidoscope of the generative modeling space and cover a wide range of topics. This book takes you on a journey where you don't just read the theory and learn about the fundamentals, but you also discover the potential and impact of these models through worked examples. We will implement these models using a variety of open-source technologies ？ the Python programming language, the TensorFlow 2 library for deep neural network development, and cloud computing resources such as Google Colab and the Kubeflow project.

Having an understanding of the various topics, models, architectures, and examples in this book will help you explore more complex topics and cutting-edge research with ease.

작가정보

저자(글) Joseph Babcock

Joseph Babcock has spent more than a decade working with big data and AI in the e-commerce, digital streaming, and quantitative finance domains. Through his career he has worked on recommender systems, petabyte scale cloud data pipelines, A/B testing, causal inference, and time series analysis. He completed his PhD studies at Johns Hopkins University, applying machine learning to the field of drug discovery and genomics.

저자(글) Raghav Bali

Raghav Bali is an author of multiple well received books and a Senior Data Scientist at one of the world's largest healthcare organizations. His work involves research and development of enterprise-level solutions based on Machine Learning, Deep Learning, and Natural Language Processing for Healthcare and Insurance-related use cases. His previous experiences include working at Intel and American Express. Raghav has a master's degree (gold medalist) from the International Institute of Information Technology, Bangalore.