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

Artificial hybrid neural networks

In the previous section, we used a GA to optimize a physical neural network.

In this section, we will extend the concept of hybrid we have just explored to ANNs. The principle is the same, so it will be relatively easy, with the concepts you now have in mind, to intuitively grasp the RNN we will optimize in this section.

The future of AI in society lies in the collective intelligence of humans (diversity), machines (AI and IoT), and nature (sustainable projects for our survival).

In AI, this diversity lies in ensemble algorithms, meta-algorithms and hybrid systems. Deep learning has proven its point. We can create a neural network with TensorFlow 2.x in a few lines. However, more often than not, it takes days, weeks, and often months to fine-tune ANN models that rely on large amounts of data to provide a reliable model. And that's where hybrid neural networks are necessary.

A deep learning network can use any form...