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.

Preface

Who this book is for

What this book covers

To get the most out of this book

Getting Started with Next-Generation Artificial Intelligence through Reinforcement Learning

Getting Started with Next-Generation Artificial Intelligence through Reinforcement Learning

Reinforcement learning concepts

How to adapt to machine thinking and become an adaptive thinker

Overcoming real-life issues using the three-step approach

The lessons of reinforcement learning

Further reading

Free Chapter

Building a Reward Matrix – Designing Your Datasets

Building a Reward Matrix – Designing Your Datasets

Designing datasets – where the dream stops and the hard work begins

Logistic activation functions and classifiers

Further reading

Machine Intelligence – Evaluation Functions and Numerical Convergence

Machine Intelligence – Evaluation Functions and Numerical Convergence

Tracking down what to measure and deciding how to measure it

Evaluating beyond human analytic capacity

Using supervised learning to evaluate a result that surpasses human analytic capacity

Further reading

Optimizing Your Solutions with K-Means Clustering

Optimizing Your Solutions with K-Means Clustering

Dataset optimization and control

Implementing a k-means clustering solution

Further reading

How to Use Decision Trees to Enhance K-Means Clustering

How to Use Decision Trees to Enhance K-Means Clustering

Unsupervised learning with KMC with large datasets

Further reading

Innovating AI with Google Translate

Innovating AI with Google Translate

Understanding innovation and disruption in AI

Discover a world of opportunities with Google Translate

AI as a new frontier

Further reading

Optimizing Blockchains with Naive Bayes

Optimizing Blockchains with Naive Bayes

Part I – the background to blockchain technology

PART II – using blockchains to share information in a supply chain

Part III – optimizing a supply chain with naive Bayes in a blockchain process

Further reading

Solving the XOR Problem with a Feedforward Neural Network

Solving the XOR Problem with a Feedforward Neural Network

The original perceptron could not solve the XOR function

Building an FNN from scratch

Applying the FNN XOR function to optimizing subsets of data

Further reading

Abstract Image Classification with Convolutional Neural Networks (CNNs)

Abstract Image Classification with Convolutional Neural Networks (CNNs)

Introducing CNNs

Training a CNN model

Further reading and references

Conceptual Representation Learning

Conceptual Representation Learning

Generating profit with transfer learning

Domain learning

Further reading

Combining Reinforcement Learning and Deep Learning

Combining Reinforcement Learning and Deep Learning

Planning and scheduling today and tomorrow

CRLMM applied to an automated apparel manufacturing process

Building the RL-DL-CRLMM

Further reading

AI and the Internet of Things (IoT)

AI and the Internet of Things (IoT)

The public service project

Setting up the RL-DL-CRLMM model

Adding an SVM function

Running the CRLMM

Further reading

Visualizing Networks with TensorFlow 2.x and TensorBoard

Visualizing Networks with TensorFlow 2.x and TensorBoard

Exploring the output of the layers of a CNN in two steps with TensorFlow

Analyzing the accuracy of a CNN using TensorBoard

Further reading

Preparing the Input of Chatbots with Restricted Boltzmann Machines (RBMs) and Principal Component Analysis (PCA)

Preparing the Input of Chatbots with Restricted Boltzmann Machines (RBMs) and Principal Component Analysis (PCA)

Defining basic terms and goals

Introducing and building an RBM

Using the weights of an RBM as feature vectors for PCA

Further reading

Setting Up a Cognitive NLP UI/CUI Chatbot

Setting Up a Cognitive NLP UI/CUI Chatbot

Adding fulfillment functionality to an agent

Machine learning agents

Further reading

Improving the Emotional Intelligence Deficiencies of Chatbots

Improving the Emotional Intelligence Deficiencies of Chatbots

From reacting to emotions, to creating emotions

Creating emotions

RNN research for future automatic dialog generation

Further reading

Genetic Algorithms in Hybrid Neural Networks

Genetic Algorithms in Hybrid Neural Networks

Understanding evolutionary algorithms

Artificial hybrid neural networks

Further reading

Neuromorphic Computing

Neuromorphic Computing

Neuromorphic computing

Getting started with Nengo

Applying Nengo's unique approach to critical AI research areas

Further reading

Quantum Computing

Quantum Computing

The rising power of quantum computers

A thinking quantum computer

Further reading

Answers to the Questions

Chapter 1 – Getting Started with Next-Generation Artificial Intelligence through Reinforcement Learning

Chapter 2 – Building a Reward Matrix – Designing Your Datasets

Chapter 3 – Machine Intelligence – Evaluation Functions and Numerical Convergence

Chapter 4 – Optimizing Your Solutions with K-Means Clustering

Chapter 5 – How to Use Decision Trees to Enhance K-Means Clustering

Chapter 6 – Innovating AI with Google Translate

Chapter 7 – Optimizing Blockchains with Naive Bayes

Chapter 8 – Solving the XOR Problem with a Feedforward Neural Network

Chapter 9 – Abstract Image Classification with Convolutional Neural Networks (CNNs)

Chapter 10 – Conceptual Representation Learning

Chapter 11 – Combining Reinforcement Learning and Deep Learning

Chapter 12 – AI and the Internet of Things

Chapter 13 – Visualizing Networks with TensorFlow 2.x and TensorBoard

Chapter 14 – Preparing the Input of Chatbots with Restricted Boltzmann Machines (RBMs) and Principal Component Analysis (PCA)

Chapter 15 – Setting Up a Cognitive NLP UI/CUI Chatbot

Chapter 16 – Improving the Emotional Intelligence Deficiencies of Chatbots

Chapter 17 – Genetic Algorithms in Hybrid Neural Networks

Chapter 18 – Neuromorphic Computing

Chapter 19 – Quantum Computing

Other Books You May Enjoy

Other Books You May Enjoy

Index

Customer Reviews

5 star

0

4 star

0

3 star

0

2 star

0

1 star

0

Abstract Image Classification with Convolutional Neural Networks (CNNs)

The invention of convolutional neural networks (CNNs) applied to vision represents by far one of the most innovative achievements in the history of applied mathematics. With their multiple layers (visible and hidden), CNNs have brought artificial intelligence from machine learning to deep learning.

In Chapter 8, Solving the XOR Problem with a Feedforward Neural Network, we saw that f(x, w) is the building block of any neural network. A function f will transform an input x with weights w to produce an output. This output can be used as such or fed into another layer. In this chapter, we will generalize this principle and introduce several layers. At the same time, we will use datasets with images. We will have a dataset for training and a dataset for validation to confirm that our model works.

A CNN relies on two basic tools of linear algebra: kernels and functions, applying...