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

Solving the XOR Problem with a Feedforward Neural Network

In the course of a corporate project, there always comes the point when a problem that seems impossible to solve hits you. At that point, you try everything you've learned, but it doesn't work for what's asked of you. Your team or customer begins to look elsewhere. It's time to react.

In this chapter, an impossible-to-solve business case regarding material optimization will be resolved successfully with a hand-made version of a feedforward neural network (FNN) with backpropagation.

Feedforward networks are one of the key building blocks of deep learning. The battle around the XOR function perfectly illustrates how deep learning regained popularity in corporate environments. XOR is an exclusive OR function that we will explore later in this chapter. The XOR FNN illustrates one of the critical functions of neural networks: classification. Once information becomes classified into subsets...