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.

Related Content you might be interested in

Current Title:

Small book image
AI Crash Course
Hadelin de Ponteves
Nov, 2019 | 360 pages
Small book image
Hands-On Q-Learning with Python
Nazia Habib
Apr, 2019 | 212 pages
Small book image
PyTorch 1.x Reinforcement Learning Cookbook
Mr. Yuxi (Hayden) Liu
Oct, 2019 | 340 pages
Small book image
The Reinforcement Learning Workshop
Alessandro Palmas | Emanuele Ghelfi | Alexandra Galina Petre | Mayur Kulkarni | Anand N. S. | Quan Nguyen | Aritra Sen | Anthony So | Saikat Basak | Sasikanth Kotti | Alberto Boschetti | Vlad Sebastian Ionescu | Richard Brooker
Aug, 2020 | 822 pages
Table of Contents (17 chapters)
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
Welcome to the Robot World
Welcome to the Robot World
Beginning the AI journey
Four different AI models
Where can learning AI take you?
Summary
2
Discover Your AI Toolkit
Discover Your AI Toolkit
The GitHub page
Colaboratory
Summary
3
Python Fundamentals – Learn How to Code in Python
Python Fundamentals – Learn How to Code in Python
Displaying text
Variables and operations
Lists and arrays
if statements and conditions
for and while loops
Functions
Classes and objects
Summary
4
AI Foundation Techniques
AI Foundation Techniques
What is Reinforcement Learning?
The five principles of Reinforcement Learning
Summary
5
Your First AI Model – Beware the Bandits!
Your First AI Model – Beware the Bandits!
The multi-armed bandit problem
The Thompson Sampling model
Summary
6
AI for Sales and Advertising – Sell like the Wolf of AI Street
AI for Sales and Advertising – Sell like the Wolf of AI Street
Problem to solve
Building the environment inside a simulation
AI solution and intuition refresher
Implementation
Summary
7
Welcome to Q-Learning
Welcome to Q-Learning
The Maze
The whole Q-learning process
Summary
8
AI for Logistics – Robots in a Warehouse
AI for Logistics – Robots in a Warehouse
Building the environment
Implementation
Summary
9
Going Pro with Artificial Brains – Deep Q-Learning
Going Pro with Artificial Brains – Deep Q-Learning
Predicting house prices
Deep learning theory
Deep Q-learning
Summary
10
AI for Autonomous Vehicles – Build a Self-Driving Car
AI for Autonomous Vehicles – Build a Self-Driving Car
Building the environment
AI solution refresher
Implementation
The demo
Summary
11
AI for Business – Minimize Costs with Deep Q-Learning
AI for Business – Minimize Costs with Deep Q-Learning
Problem to solve
Building the environment
AI solution
The demo
Recap – The general AI framework/Blueprint
Summary
12
Deep Convolutional Q-Learning
Deep Convolutional Q-Learning
What are CNNs used for?
How do CNNs work?
Deep convolutional Q-learning
Summary
13
AI for Games – Become the Master at Snake
AI for Games – Become the Master at Snake
Problem to solve
Building the environment
AI solution
Implementation
The demo
Summary
14
Recap and Conclusion
Recap and Conclusion
Recap – The general AI framework/blueprint
Exploring what's next for you in AI
15
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think
16
Index
Index

Summary

In this first practical tutorial, you implemented Thompson Sampling to solve the multi-armed bandit problem as applied to an advertising campaign. Thompson Sampling was able to find the best business strategy quickly, something which Random Selection was unable to do. In total you generated 91% of relative return, which, after making some assumptions, would generate an extra 2 billion dollars in revenue. You did that in just one file in less than 60 lines of code. Quite astounding, right?

Previous Section
End of Chapter 6
Next Chapter