Browse Library
Sign In Start Free Trial
Close icon Search icon
Account
Browse Library Sign In Start Free Trial

Add to playlist

Create a Playlist

Modal Close icon
You need to login to use this feature.
  • Book Overview & Buying Deep Learning with TensorFlow 2 and Keras
  • Table Of Contents Toc
Deep Learning with TensorFlow 2 and Keras

Deep Learning with TensorFlow 2 and Keras - Second Edition

By : Antonio Gulli, Dr. Amita Kapoor, Sujit Pal
4.3 (26)
Buy this Book
close
close
Deep Learning with TensorFlow 2 and Keras

Deep Learning with TensorFlow 2 and Keras

4.3 (26)
By: Antonio Gulli, Dr. Amita Kapoor, Sujit Pal
Buy this Book

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

Convolutional Neural Networks

In the previous chapters we have discussed DenseNets, in which each layer is fully connected to the adjacent layers. We looked at one application of these dense networks in classifying the MNIST handwritten characters dataset. In that context, each pixel in the input image has been assigned to a neuron with a total of 784 (28 × 28 pixels) input neurons. However, this strategy does not leverage the spatial structure and relationships between each image. In particular, this piece of code is a DenseNet that transforms the bitmap representing each written digit into a flat vector where the local spatial structure is removed. Removing the spatial structure is a problem because important information is lost:

#X_train is 60000 rows of 28x28 values --> reshaped in 60000 x 784
X_train = X_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784)

Convolutional neural networks (in short, convnets or CNNs) leverage spatial information...

CONTINUE READING
83
Tech Concepts
36
Programming languages
73
Tech Tools
Icon Unlimited access to the largest independent learning library in tech of over 8,000 expert-authored tech books and videos.
Icon Innovative learning tools, including AI book assistants, code context explainers, and text-to-speech.
Icon 50+ new titles added per month and exclusive early access to books as they are being written.
Deep Learning with TensorFlow 2 and Keras
End of Section 4
Next Section
notes
bookmark Notes and Bookmarks search Search in title playlist Add to playlist download Download options
font-size Font size

Change the font size

margin-width Margin width

Change margin width

day-mode Day/Sepia/Night Modes

Change background colour

Close icon Search
Country selected
Close icon Your notes and bookmarks

Confirmation

Modal Close icon
claim successful
Order Page Read Now

Buy this book with your credits?

Modal Close icon
Are you sure you want to buy this book with one of your credits?
Close
YES, BUY

Submit Your Feedback

Modal Close icon
Modal Close icon
Modal Close icon