Key Features

• Understand the fundamentals of deep learning and machine learning through clear explanations and extensive code samples
• Implement graph neural networks, transformers using Hugging Face and TensorFlow Hub, and joint and contrastive learning
• Learn cutting-edge machine and deep learning techniques

Book Description

Deep Learning with TensorFlow and Keras teaches you neural networks and deep learning techniques using TensorFlow (TF) and Keras. You'll learn how to write deep learning applications in the most powerful, popular, and scalable machine learning stack available.

TensorFlow 2.x focuses on simplicity and ease of use, with updates like eager execution, intuitive higher-level APIs based on Keras, and flexible model building on any platform. This book uses the latest TF 2.0 features and libraries to present an overview of supervised and unsupervised machine learning models and provides a comprehensive analysis of deep learning and reinforcement learning models using practical examples for the cloud, mobile, and large production environments.

This book also shows you how to create neural networks with TensorFlow, runs through popular algorithms (regression, convolutional neural networks (CNNs), transformers, generative adversarial networks (GANs), recurrent neural networks (RNNs), natural language processing (NLP), and graph neural networks (GNNs)), covers working example apps, and then dives into TF in production, TF mobile, and TensorFlow with Keras.

What you will learn

• Learn how to use the popular GNNs with TensorFlow to carry out graph mining tasks
• Discover the world of transformers, from pretraining to fine-tuning to evaluating them
• Apply self-supervised learning to natural language processing, computer vision, and audio signal processing
• Combine probabilistic and deep learning models using TensorFlow Probability
• Train your models on the cloud and put TF to work in real environments
• Build machine learning and deep learning systems with TensorFlow 2.x and the Keras API

Who this book is for

This hands-on machine learning book is for Python developers and data scientists who want to build machine learning and deep learning systems with TensorFlow. This book gives you the theory and practice required to use Keras, TensorFlow, and AutoML to build machine learning systems.

Some machine learning knowledge would be useful. We don't assume TF knowledge.

Table of Contents

1. Neural Networks Foundations with TF
2. Regression and Classification
3. Convolutional Neural Networks
4. Word Embeddings
5. Recurrent Neural Network
6. Transformers
7. Unsupervised Learning
8. Autoencoders
9. Generative Models
10. Self-Supervised Learning
11. Reinforcement Learning
12. Probabilistic TensorFlow
13. An Introduction to AutoML
14. The Math Behind Deep Learning
15. Tensor Processing Unit
16. Other Useful Deep Learning Libraries
17. Graph Neural Networks
18. Machine Learning Best Practices
19. TensorFlow 2 Ecosystem
20. Advanced Convolutional Neural Networks

Review

“Packt recently sent me a review copy of this book, and I was seriously impressed. The book focuses admirably well on the practical side of many variants of neural networks (and a few non-NN approaches to ML tasks, such as k-means clustering for unsupervised learning). Readers also get to see actual Python code implementing each of the NN variants (mostly, as the title says, with Keras and TensorFlow). The code is always kept very simple and readable but is quite usable as-is, although it's most useful as a springboard to customization, tweaks, and optimization for the reader's specific purposes.”

Alex Martelli, Python Software Foundation Fellow, Co-author of Python Cookbook and Python in a Nutshell

"Approachable, well-written, with a great balance between theory and practice. A very enjoyable introduction to machine learning for software developers."

François Chollet, Creator of Keras

"We have used the first two editions (and will now use the third edition) of this book in my course at the University of Oxford (Artificial Intelligence: Cloud and Edge Implementations). Both Antonio Gulli and Amita Kapoor are also tutors on our course. This shows our confidence in the expanding body of knowledge covered in this book. It's great to see that the book now includes topics like TensorFlow probability, Graph neural networks, AutoML, and Advanced CNN models. We look forward to using this book in our class in the fall and are happy to recommend it to others."

Ajit Jaokar, Course Director – Artificial Intelligence: Cloud and Edge Implementations, University of Oxford

“This book provides a really good overview of ML models that you will find in use in production today. When they talk about Transformers, for example, they link back to earlier concepts (such as attention). They also talk about common variants of Transformers, such as retaining only the encoder or only the decoder, which provides a bridge to BERT and GPT that are covered in later chapters. This makes the book comprehensive (since models are covered historically), practical (only models that are commonly implemented), and approachable (since the ideas are built one-by-one).

I strongly recommend this book if you want to get a handle on deep learning.

Valliappa Lakshmanan, Data Scientist and Author, Machine Learning Design Patterns

About the Author

Amita Kapoor taught and supervised research in neural networks and artificial intelligence for 20+ years as Associate Professor in SRCASW, University of Delhi. She now provides her expertise in AI and EduTech to various organizations and companies.

Antonio Gulli has a passion for establishing and managing global technological talent for innovation and execution. His core expertise is in cloud computing, deep learning, and search engines. Currently, Antonio works for Google in the Cloud Office of the CTO in Zurich, working on Search, Cloud Infra, Sovereignty, and Conversational AI.

Sujit Pal is a Technology Research Director at Elsevier Labs, an advanced technology group within the Reed-Elsevier Group of companies. His interests include semantic search, natural language processing, machine learning, and deep learning. At Elsevier, he has worked on several initiatives involving search quality measurement and improvement, image classification and duplicate detection, and annotation and ontology development for medical and scientific corpora.