Practical Deep Learning Fundamentals – Kris Bolton Scroll to top

Coming 11th January 2019

Practical Deep Learning Fundamentals

From Concept to Implementation of Neural Networks and Deep Learning.


Chapter One: Preface

An introduction to the subjects covered in the book, who the book is for and why the contents is of value.

Chapter Three: An Introduction to Machine Learning

An introduction to the board area of machine learning, providing the reader with a foundation to build on as further concepts are discussed.

Chapter Five: Deep Learning

In chapter seven we delve into deep learning, learning about the vast array of neural network architectures that have driven interest in machine learning.

Chapter Seven: How to Evaluate and Tune Neural Networks

In chapter seven we discuss how to evaluate and tune neural networks for the specific use the reader has designed.

Chapter Nine: Best Practices for Building Data Sets

Here best practices for building the data sets which will be used by your network are discussed and justified.

Chapter Eleven: Project: Sentiment Analysis

Utilising Google’s TensorFlow we will implement a neural network from a research paper to analyse a real world data set.

Chapter Thirteen: Project: Object Recognition

We will use an open source library to recognise objects in images.

Chapter Fifteen: Project: Reinforcement Learning

We will implement a Reinforcement Learning algorithm into an open source library.

Chapter Seventeen: The Math of Neural Networks

A quick introduction to various aspects of maths the reader will come across while reading research papers, or reading more widely about machine learning.

Chapter Two: Why You Should Get into Machine Learning

A discussion of the mergers, acquisitions, commercial demand, breakthroughs and more that make machine learning profitable and interesting to get into.

Chapter Four: An Overview of Machine Learning Libraries

An introduction to the most popular machine learning libraries to give the reader a broad understanding of the open source landscape for their own projects.

Chapter Six: Artificial Neural Networks

Artificial Neural Networks and the concepts surrounding them are introduced through illustration and pseudocode. The reader is also presented with a task to implement a single neuron program to analyse a data set.

Chapter Eight: Training Neural Networks

Chapter eight discusses how neural networks are trained and the various technical aspects which affect the success of neural network training.

Chapter Ten: Introduction to TensorFlow

An in-depth introduction to TensorFlow, as preparation for its use within projects in the preceding chapters.

Chapter Twelve: Project: TBD

This project has yet to be determined.

Chapter Fourteen: Project: TBD

This project has yet to be determined.

Chapter Sixteen: Project: TBD

This project has yet to be determined.

Chapter Eighteen: Further Reading and What to do Next

A discussion and list of resources for further reading to improve understanding further and websites to keep up to date on machine learning news.


This book has been written to be approachable to readers of all backgrounds. Detailed explanations and illustrations provide insight into the often complex principles and methodologies of machine learning.

On the occasions where technical jargon becomes dense and the readability of the section is reduced, ‘Jargon Buster’ sections are used to break down the jargon into understandable more English.

Practical Exercises

This book is written to leave the reader with practical and usable skills. From the beginning the reader will create programs to build understanding of core concepts, ultimately moving onto larger, more complex projects.

The first such project guides the reader through the implementation of a Perceptron in Python’s Scikit-learn library with the aim of correctly predicting flower types from the Iris data set. This exercise is perfectly placed as an introduction to how basic neural networks operate and give a glimpse into what can be achieved.

"Just enough math"

This book implements a “just enough math” approach. Math is used for illustration within this book and is understandable by anyone with a high school level of math. You do not need to be a math whizz to understand machine learning – not with this book.

If the reader historically struggled with math, this book provides a softer approach than many books on machine learning and is significantly more approachable than text books on the subject. By the end of this book you will have usable skills and knowledge of machine learning.

Practical Deep Learning Fundamentals

Read the First Four Chapters

Sign up below and receive the first chapter, and the following three as they are released!

The Ultimate Package

Book + Videos + Code Files + More

The Ultimate Package provides all the resources you will need to explore deep learning through practical experiments with multiple open source libraries. Tutorial and theory videos guide the reader through examples and projects. Python code files allow the reader to easily follow the tutorials and learn by doing. Additionally, custom software, Tweet Annotation Tool makes it easier to create your own twitter data sets for exploring Sentiment Analysis and Opinion Mining.

The Book + Code Files

A solid introduction to Deep Learning

Eighteen chapters of machine learning goodness, numerous examples and tutorials, and six in-depth projects. The culmination of hundreds of hours of research, writing and design. No matter your background you will learn something new – unless you happen to have a MSc/PhD in Data Science. Includes example and project code files. You’ll use multiple open source libraries and analyse real data. You won’t regret this purchase.


What format is the book provided in?

The book is provided in PDF format. Due to design considerations it is not possible to offer .mobi, .epub or other formats.

What are the differences between the packages?

There are two tiers of packages. The Book + Files, which is simply the book in PDF format along with iPython notebook files. The Ultimate Package, contains the book, python code files, videos and the twitter annotation tool. Intended to give a comprehensive introduction to machine learning. It’s really down to your budget which one is best for you.

Can I return the book if I don't like it?

Yes. If you don’t like the book reply to your receipt email within 14 days and I will refund you. Pre-orders will be refunded from the date of launch.

I have more questions, how can I get in touch?

If you have any questions or feedback, they are gratefully received. Please see the contact page for specific contact information.