Sign In Start Free Trial

Book Overview & Buying
Table Of Contents
Feedback & Rating

Deep Learning with TensorFlow

By : Zaccone, Karim

3 (4)

Deep Learning with TensorFlow

3 (4)

By: Zaccone, Karim

Overview of this book

Deep learning is a branch of machine learning algorithms based on learning multiple levels of abstraction. Neural networks, which are at the core of deep learning, are being used in predictive analytics, computer vision, natural language processing, time series forecasting, and to perform a myriad of other complex tasks. This book is conceived for developers, data analysts, machine learning practitioners and deep learning enthusiasts who want to build powerful, robust, and accurate predictive models with the power of TensorFlow, combined with other open source Python libraries. Throughout the book, you’ll learn how to develop deep learning applications for machine learning systems using Feedforward Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks, Autoencoders, and Factorization Machines. Discover how to attain deep learning programming on GPU in a distributed way. You'll come away with an in-depth knowledge of machine learning techniques and the skills to apply them to real-world projects.

Preface

Preface

Who this book is for

What this book covers

To get the most out of this book

Get in touch

Free Chapter

1. Getting Started with Deep Learning

1. Getting Started with Deep Learning

A soft introduction to machine learning

Artificial neural networks

How does an ANN learn?

Neural network architectures

Deep learning frameworks

Summary

2. A First Look at TensorFlow

2. A First Look at TensorFlow

A general overview of TensorFlow

What's new from TensorFlow v1.6 forwards?

Installing and configuring TensorFlow

TensorFlow computational graph

TensorFlow code structure

Data model in TensorFlow

Visualizing computations through TensorBoard

Linear regression and beyond

Summary

3. Feed-Forward Neural Networks with TensorFlow

3. Feed-Forward Neural Networks with TensorFlow

Feed-forward neural networks (FFNNs)

Implementing a feed-forward neural network

Implementing a multilayer perceptron (MLP)

Tuning hyperparameters and advanced FFNNs

Summary

4. Convolutional Neural Networks

4. Convolutional Neural Networks

Main concepts of CNNs

CNNs in action

LeNet5

Implementing a LeNet-5 step by step

Dataset preparation

Fine-tuning implementation

Inception-v3

Emotion recognition with CNNs

Summary

5. Optimizing TensorFlow Autoencoders

5. Optimizing TensorFlow Autoencoders

How does an autoencoder work?

Implementing autoencoders with TensorFlow

Improving autoencoder robustness

Fraud analytics with autoencoders

Summary

6. Recurrent Neural Networks

6. Recurrent Neural Networks

Working principles of RNNs

RNN and the gradient vanishing-exploding problem

Implementing an RNN for spam prediction

Developing a predictive model for time series data

An LSTM predictive model for sentiment analysis

Human activity recognition using LSTM model

Summary

7. Heterogeneous and Distributed Computing

7. Heterogeneous and Distributed Computing

GPGPU computing

The TensorFlow GPU setup

Distributed computing

The distributed TensorFlow setup

Summary

8. Advanced TensorFlow Programming

8. Advanced TensorFlow Programming

tf.estimator

TFLearn

PrettyTensor

Keras

Summary

9. Recommendation Systems Using Factorization Machines

9. Recommendation Systems Using Factorization Machines

Recommendation systems

Movie recommendation using collaborative filtering

Factorization machines for recommendation systems

Improved factorization machines

Summary

10. Reinforcement Learning

10. Reinforcement Learning

The RL problem

OpenAI Gym

The Q-Learning algorithm

Deep Q-learning

Summary

Other Books You May Enjoy

Other Books You May Enjoy

Leave a review – let other readers know what you think

Index

Index

Customer Reviews

3 (4)

5 star

25%

4 star

0

3 star

50%

2 star

0

1 star

25%

Preface

Every week, we follow news of applications and the shocking results obtained from them, thanks to the artificial intelligence algorithms applied in different fields. What we are witnessing is one of the biggest accelerations in the entire history of this sector, and the main suspect behind these important developments is called deep learning.

Deep learning comprises a vast set of algorithms that are based on the concept of neural networks and expand to contain a huge number of nodes that are disseminated at several levels of depth.

Though the concept of neural networks, the so-called Artificial Neural Network (ANN), dates back to the late 1940s, initially, they were difficult to be used because of the need for huge computational power resources and the lack of data required to train the algorithms. Presently, the ability to use graphics processors (GPUs) in parallel to perform intensive calculation operations has completely opened the way to the use of deep learning.

In this context, we propose the second edition of this book, with expanded and revised contents that introduce the core concepts of deep learning, using the last version of TensorFlow.

TensorFlow is Google's open-source framework for the mathematical, Machine Learning, and Deep Learning capabilities, released in 2011. Subsequently, TensorFlow has been widely adopted in academia, research, and industry. Recently, the most stable version 1.6 has been released with a unified API. The most stable version of TensorFlow at the time of writing was version 1.6, which was released with a unified API and is thus a significant and stable version in the TensorFlow roadmap. This book also discusses and is compliant with the pre-release version, 1.7, which was available during the production stages of this book.

TensorFlow provides the flexibility needed to implement and research cutting-edge architectures, while allowing users to focus on the structure of their models as opposed to mathematical details.

You will learn deep learning programming techniques with hands-on model building, data collection, transformation, and much more!

Enjoy reading!

Search

Your notes and bookmarks