Build Your Own Neural Network in Python

What’s the first thing that comes to your mind when you think of machine learning?

And you start thinking, I need a PhD in 10 different disciplines just to get started with this!

But what if machine learning wasn’t so hard? What if you could build your own Neural Network from scratch, using basic Python?

Introducing Neural Networks

Neural Networks are machine learning algorithms loosely modeled on the human brain. They are great at solving complex problems like image recognition and speech processing.

Even though Neural Networks can solve complex problems, their implementation is fairly easy, and only uses high school level maths (and if even that scares you, I will cover all the maths required with examples).

To reiterate: We will be using very little maths. The focus will be on practical stuff.

What we will go over in this eBook:

  1. Theory behind Neural Networks

  2. A simplified intro to the maths behind neural networks

  3. Back propagation, multiple layers and more

  4. A complex example, like recognise handwritten digits

  5. Keras introduction

  6. Case Studies: Identify images using machine learning, build a movies sentiment analysis app.

How much knowledge of Machine Learning do you need?


How good do you have to be with Python?

You must know the basics. That’s all. We’ll be using libraries like numpy/scipy, but I will introduce them as I use them.

Why Machine Learning?

Machine Learning is one of the hottest fields today, with great job opportunities. Even non-software companies hire machine learning experts, to study things like customer behaviour, buying habits etc.

Neural Networks are a great way to get started in machine learning.

Based on my Kickstarter:


Yes, I want the book!

If the button above doesn’t work, go here Right click, and choose Open in new window.