Book Image

Artificial Intelligence By Example - Second Edition

By : Denis Rothman
Book Image

Artificial Intelligence By Example - Second Edition

By: Denis Rothman

Overview of this book

AI has the potential to replicate humans in every field. Artificial Intelligence By Example, Second Edition serves as a starting point for you to understand how AI is built, with the help of intriguing and exciting examples. This book will make you an adaptive thinker and help you apply concepts to real-world scenarios. Using some of the most interesting AI examples, right from computer programs such as a simple chess engine to cognitive chatbots, you will learn how to tackle the machine you are competing with. You will study some of the most advanced machine learning models, understand how to apply AI to blockchain and Internet of Things (IoT), and develop emotional quotient in chatbots using neural networks such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs). This edition also has new examples for hybrid neural networks, combining reinforcement learning (RL) and deep learning (DL), chained algorithms, combining unsupervised learning with decision trees, random forests, combining DL and genetic algorithms, conversational user interfaces (CUI) for chatbots, neuromorphic computing, and quantum computing. By the end of this book, you will understand the fundamentals of AI and have worked through a number of examples that will help you develop your AI solutions.
Table of Contents (23 chapters)
21
Other Books You May Enjoy
22
Index

Adding an SVM function

The self-driving car has delivered its packages to the shelters. Now it has to find a parking lot and park there. Instead of having a base like many other systems, this saves the city the cost of many useless trips.

Motivation – using an SVM to increase safety levels

The support vector system adds a new function to itinerary calculations—safety.

Most systems, such as Google Maps, focus on:

  • The shortest trip
  • The fastest trip
  • Traffic

However, self-driving cars have to take extra precautions. Many humans do not feel secure on some roads. Safety comes first, no matter what. Once a suitable parking lot has been found, the SVM has to avoid traffic.

The goal is to find a path through traffic, even if the distance is longer. A p parameter allows for a p% variance in the distance. For example, 10% allows a 10% longer distance and will provide safe passage, as shown in the following SVM result:

...