Book Image

Deep Learning with TensorFlow 2 and Keras - Second Edition

By : Antonio Gulli, Amita Kapoor, Sujit Pal
Book Image

Deep Learning with TensorFlow 2 and Keras - Second Edition

By: Antonio Gulli, Amita Kapoor, Sujit Pal

Overview of this book

Deep Learning with TensorFlow 2 and Keras, Second Edition teaches neural networks and deep learning techniques alongside 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 is the machine learning library of choice for professional applications, while Keras offers a simple and powerful Python API for accessing TensorFlow. TensorFlow 2 provides full Keras integration, making advanced machine learning easier and more convenient than ever before. This book also introduces neural networks with TensorFlow, runs through the main applications (regression, ConvNets (CNNs), GANs, RNNs, NLP), covers two working example apps, and then dives into TF in production, TF mobile, and using TensorFlow with AutoML.

Related Content you might be interested in

Current Title:

Small book image
Deep Learning with TensorFlow 2 and Keras - Second Edition
Antonio Gulli | Amita Kapoor | Sujit Pal
Dec, 2019 | 646 pages
Small book image
Deep Learning with Keras
Sujit Pal | Antonio Gulli
Apr, 2017 | 318 pages
Small book image
TensorFlow 1.x Deep Learning Cookbook
Amita Kapoor | Antonio Gulli
Dec, 2017 | 536 pages
Small book image
Generative AI with Python and TensorFlow 2
Raghav Bali | Joseph Babcock
Apr, 2021 | 488 pages
Table of Contents (19 chapters)
Preface
Preface
Mission
Machine learning, artificial intelligence, and the deep learning Cambrian explosion
Who this book is for
What this book covers
What you need for this book
Get in touch
References
Free Chapter
1
Neural Network Foundations with TensorFlow 2.0
Neural Network Foundations with TensorFlow 2.0
What is TensorFlow (TF)?
What is Keras?
What are the most important changes in TensorFlow 2.0?
Introduction to neural networks
Perceptron
Multi-layer perceptron – our first example of a network
A real example – recognizing handwritten digits
Regularization
Playing with Google Colab – CPUs, GPUs, and TPUs
Sentiment analysis
Hyperparameter tuning and AutoML
Predicting output
A practical overview of backpropagation
What have we learned so far?
Towards a deep learning approach
References
2
TensorFlow 1.x and 2.x
TensorFlow 1.x and 2.x
Understanding TensorFlow 1.x
Understanding TensorFlow 2.x
The TensorFlow 2.x ecosystem
Keras or tf.keras?
Summary
3
Regression
Regression
What is regression?
Prediction using linear regression
TensorFlow Estimators
Predicting house price using linear regression
Classification tasks and decision boundaries
Summary
References
4
Convolutional Neural Networks
Convolutional Neural Networks
Deep Convolutional Neural Network (DCNN)
An example of DCNN ‒ LeNet
Recognizing CIFAR-10 images with deep learning
Very deep convolutional networks for large-scale image recognition
Summary
References
5
Advanced Convolutional Neural Networks
Advanced Convolutional Neural Networks
Computer vision
Video
Textual documents
Audio and music
A summary of convolution operations
Capsule networks
Summary
References
6
Generative Adversarial Networks
Generative Adversarial Networks
What is a GAN?
Deep convolutional GAN (DCGAN)
Some interesting GAN architectures
Cool applications of GANs
CycleGAN in TensorFlow 2.0
Summary
References
7
Word Embeddings
Word Embeddings
Word embedding ‒ origins and fundamentals
Distributed representations
Static embeddings
Creating your own embedding using gensim
Exploring the embedding space with gensim
Using word embeddings for spam detection
Neural embeddings – not just for words
Character and subword embeddings
Dynamic embeddings
Sentence and paragraph embeddings
Language model-based embeddings
Summary
References
8
Recurrent Neural Networks
Recurrent Neural Networks
The basic RNN cell
RNN cell variants
RNN variants
RNN topologies
Encoder-Decoder architecture – seq2seq
Attention mechanism
Transformer architecture
Summary
References
9
Autoencoders
Autoencoders
Introduction to autoencoders
Vanilla autoencoders
Sparse autoencoder
Denoising autoencoders
Stacked autoencoder
Summary
References
10
Unsupervised Learning
Unsupervised Learning
Principal component analysis
Self-organizing maps
Restricted Boltzmann machines
Variational Autoencoders
Summary
References
11
Reinforcement Learning
Reinforcement Learning
Introduction
Introduction to OpenAI Gym
Deep Q-Networks
Deep deterministic policy gradient
Summary
References
12
TensorFlow and Cloud
TensorFlow and Cloud
Deep learning on cloud
Virtual machines on cloud
Jupyter Notebooks on cloud
TensorFlow Extended for production
TensorFlow Enterprise
Summary
References
13
TensorFlow for Mobile and IoT and TensorFlow.js
TensorFlow for Mobile and IoT and TensorFlow.js
TensorFlow Mobile
TensorFlow Lite
Pretrained models in TensorFlow Lite
An overview of federated learning at the edge
TensorFlow.js
Summary
References
14
An introduction to AutoML
An introduction to AutoML
What is AutoML?
Achieving AutoML
Automatic data preparation
Automatic feature engineering
Automatic model generation
AutoKeras
Google Cloud AutoML
Bringing Google AutoML to Kaggle
Summary
References
15
The Math Behind Deep Learning
The Math Behind Deep Learning
History
Some mathematical tools
Activation functions
Backpropagation
Thinking about backpropagation and convnets
Thinking about backpropagation and RNNs
A note on TensorFlow and automatic differentiation
Summary
References
16
Tensor Processing Unit
Tensor Processing Unit
C/G/T processing units
Three generations of TPUs and Edge TPU
TPU performance
How to use TPUs with Colab
Using pretrained TPU models
Using TensorFlow 2.1 and nightly build
Summary
References
17
Other Books You May Enjoy
Other Books You May Enjoy
18
Index
Index

Tensor Processing Unit

This chapter introduces the Tensor Processing Unit (TPU), a special chip developed at Google for ultra-fast execution of neural network mathematical operations. Similarly to Graphic Processing Units (GPUs), the idea here is to have a special processor focusing only on very fast matrix operations with no support for all the other operations normally supported by Central Processing Units (CPUs). However, the additional improvement with TPUs is to remove from the chip any hardware support for graphics operation normally present in GPUs (rasterization, texture mapping, frame buffer operations, and so on). Think of a TPU as a special purpose co-processor specialized for deep learning, being focused on matrix or tensor operations. In this chapter we are going to compare CPUs and GPUs with the three generations of TPUs and Edge TPUs. All these accelerators are available as November 2019. The chapter will include code examples of using TPUs. So with that, let&apos...

Previous Section
End of Section 1
Next Section