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

Neuromorphic computing

Let's go directly to the core of our thought process to understand neuromorphic computing. For AI experts, I would like to summarize the voyage from our classical models to cutting-edge neuromorphic models in a single phrase:

from mind to brain

If we take this further, M is the set of all of our mental representations and B is the world of physical reactions that lead to thinking patterns.

In this sense, M is a set of everything we have explored up to this point in this book:

M = {rule based systems, machine learning, deep learning, evolutionary algorithms … m}

m is any mathematical mental representation of the world surrounding us. In deep learning, for example, an artificial neural network will try to make sense of the chaos of an image by searching the patterns it can find in an image through lower dimensions and higher levels of abstraction.

However, a mental construction, no matter how efficient it seems, remains...