Book Image

AI Crash Course

By : Hadelin de Ponteves
5 (4)
Book Image

AI Crash Course

5 (4)
By: Hadelin de Ponteves

Overview of this book

Welcome to the Robot World … and start building intelligent software now! Through his best-selling video courses, Hadelin de Ponteves has taught hundreds of thousands of people to write AI software. Now, for the first time, his hands-on, energetic approach is available as a book. Starting with the basics before easing you into more complicated formulas and notation, AI Crash Course gives you everything you need to build AI systems with reinforcement learning and deep learning. Five full working projects put the ideas into action, showing step-by-step how to build intelligent software using the best and easiest tools for AI programming, including Python, TensorFlow, Keras, and PyTorch. AI Crash Course teaches everyone to build an AI to work in their applications. Once you've read this book, you're only limited by your imagination.
Table of Contents (17 chapters)
16
Index

Deep learning theory

Here is our plan of attack to go pro and tackle deep learning:

  1. The neuron
  2. The activation function
  3. How do neural networks work?
  4. How do neural networks learn?
  5. Forward-propagation and back-propagation
  6. Gradient descent, including Batch, Stochastic, and Mini-Batch methods

I hope you're excited about this section—deep learning is an awesome and powerful field to study.

The neuron

The neuron is the basic building block of Artificial Neural Networks, and they are based on the neuron cells found the brain.

Biological neurons

In the following images are real-life neurons that have been smeared onto a slide, colored a little bit, and observed through a microscope:

Figure 8: The neuron

As you can see, they have the structure of a central body with lots of different branches coming out of it. The question is: How can we recreate that in a machine? We really want to recreate it in a machine, since the whole...