AI Revealed : Theory, Applications and Ethics / Herman Erik.

Format:

Book

Author/Creator:

Erik, Herman, author.

Series:

Computing and Information Technology Series

Language:

English

Subjects (All):

Artificial intelligence--Moral and ethical aspects.

Artificial intelligence.

Artificial intelligence--Social aspects.

Artificial intelligence--Philosophy.

Physical Description:

1 online resource (185 pages)

Edition:

First edition.

Place of Publication:

Boston, MA : Mercury Learning and Information, [2025]

Summary:

This book is a guide to navigating the evolving landscape of artificial intelligence.Designed for both novices and seasoned professionals it covers a broad range of topics from fundamental ideas to innovative advancements.

Contents:

Cover

Half title

Title

Copyright

Dedication

Contents

Preface

Chapter 1: The Foundations of Artificial Intelligence

What is Artificial Intelligence?

Definition of AI

Types of AI

Narrow AI

General AI

Artificial Superintelligence

Core Components of AI Systems

Machine Learning (ML)

Neural Networks

Robotics

Expert Systems

The History of AI

Early Concepts and Theories

Key Milestones

Modern Developments

Importance and Applications of AI

Transformational Impact

Healthcare

Automotive

Finance

Customer Service

Daily Life

Ethical Considerations

Fundamental Questions

Bias and Fairness

Privacy

Regulation and Governance

AI Application: Create a Simple Rule-Based Chatbot

Step 1: Set Up the Development Environment

Step 2: Create the Chatbot Script

Step 3: Run the Chatbot

Step 4: Understand the Script

Conclusion

Chapter 2: Foundations of Machine Learning

Introduction to Machine Learning

Definition and Scope

How ML Works

Key Components

Data

Model

Learning Algorithm

Evaluation Metrics

Supervised Learning

Concept and Mechanism

Common Algorithms

Linear Regression

Logistic Regression

Decision Trees

Support Vector Machines (SVMs)

Applications

Spam Detection

Sentiment Analysis

Credit Scoring Systems

Medical Diagnosis

Fraud Detection

Predictive Maintenance

Customer Churn Prediction

Stock Market Prediction

Unsupervised Learning

Clustering Algorithms

Association Algorithms

Dimensionality Reduction Techniques

Customer Segmentation

Market Basket Analysis

Anomaly Detection

Social Network Analysis

Document Clustering

Image Compression

Bioinformatics

Model Evaluation and Selection.

Evaluation Metrics

Precision and Recall

The F1 Score

Mean Squared Error (MSE) and Root Mean Squared Error (RMSE)

Area Under the Receiver Operating Characteristic Curve (AUC-ROC)

Validation Techniques

Cross-Validation

Bootstrapping

Model Selection

AI Application: Implement a Linear Regression Model to Predict House Prices

Step 2: Prepare the Dataset

Step 3: Implement the Linear Regression Model

Step 4: Run the Script

Chapter 3: Deep Learning and Neural Networks

Introduction to Deep Learning

Understanding Neural Networks

Basic Structure

How They Learn

Types of Neural Networks

Feedforward Neural Networks

Recurrent Neural Networks (RNNs)

Convolutional Neural Networks (CNNs)

Transformers

Key Architectures in Deep Learning

CNNs

RNNs

Challenges and Ethical Considerations

Computational Demands

Data Requirements

Privacy and Security

Artificial Neural Networks (ANNs)

Fundamentals of ANNs

Neuron Model

Layers of an ANN

Activation Functions

Training Neural Networks

Backpropagation

Loss Functions

Optimization Algorithms

Practical Applications of ANNs

Industrial Automation

Architecture of CNNs

Convolutional Layers

Pooling Layers

Fully Connected Layers

Functionality and Training of CNNs

Feature Learning

Backpropagation in CNNs

Advanced Training Techniques

Real-World Applications of CNNs

Facial Recognition Systems

Medical Imaging

Automotive Industry

Handling Sequential Data

Advanced Architectures

Applications of RNNs

Language Translation Services

Voice-Activated Assistants

Financial Forecasting

Advanced Architectures (for example, GANs, Transformers)

Generator.

Discriminator

Training Process

Core Mechanism

Training Efficiency

AI Application: Build a Basic Neural Network for Digit Classification Using MNIST Dataset

Step 2: Load and Preprocess the MNIST Dataset

Step 3: Create the Neural Network

Step 4: Train the Neural Network

Step 5: Evaluate the Model

Step 6: Run the Script

Chapter 4: Natural Language Processing (NLP)

Introduction to NLP

Fundamentals of NLP

Syntax

Semantics

Pragmatics

Techniques in NLP

Text Preprocessing

Parsing and Part-of-Speech Tagging

Challenges in NLP

Ambiguity and Context

Slang and Dialects

Resource Availability

Real-World Applications of NLP

Customer Service Bots

Automated Translation Services

Tokenization

Stemming

Lemmatization

Removing Stop Words

Named Entity Recognition

Machine Translation

AI Application: Perform Sentiment Analysis on a Set of Movie Reviews

Step 1: Set Up Development Environment

Step 2: Load and Preprocess the Movie Reviews Dataset

Step 3: Train the Sentiment Analysis Model

Step 4: Evaluate the Model

Step 5: Run the Script

Chapter 5: Computer Vision

Introduction to Computer Vision

Image Preprocessing

Grayscale Conversion

Histogram Equalization

Normalization

Edge Detection

Object Detection

Region-Based Convolutional Neural Networks (R-CNNs)

YOLO (You Only Look Once)

SSD (Single Shot Multidetector)

Image Classification

Machine Learning Algorithms

Image Segmentation

Thresholding

Clustering Methods

Advanced Methods.

AI Application: Implement an Image Classification Model Using CIFAR-10 Dataset

Step 2: Load and Preprocess the CIFAR-10 Dataset

Step 3: Build the Image Classification Model

Step 4: Train the Image Classification Model

Chapter 6: Ethics and Bias in AI

Ethical Considerations in AI

Bias in AI Algorithms

Fairness and Accountability

AI Application: Analyze Bias in a Dataset and Discuss Mitigation Strategies

Step 2: Load and Explore the Dataset

Step 3: Preprocess the Data

Step 4: Train a Baseline Model

Step 5: Analyze Bias in the Model

Step 6: Mitigate Bias

Step 7: Run the Script

Chapter 7: AI in Practice: Industry Case Studies

Transportation

Retail

Manufacturing

AI Application: Predicting Patient Outcomes in Healthcare

Step 2: Load and Explore the Healthcare Dataset

Step 4: Train a Predictive Model

Chapter 8: Future of AI and Emerging Technologies

Quantum Computing

Edge AI

Explainable AI

AI for Social Good

AI Application: Experiment With a Simple Quantum Computing Algorithm Using IBM's Qiskit

Step 2: Introduction to Quantum Computing Basics

Step 3: Implement a Basic Quantum Algorithm

Chapter 9: Getting Started With AI Development

Setting Up Development Environment

Introduction to Python for AI

Using Popular AI Libraries

AI Application: Set Up an AI Development Environment and Run a Basic Python Script

Step 1: Install Python

Step 2: Install Jupyter Notebook.

Step 3: Set Up a Virtual Environment (optional but recommended)

Step 4: Create and Run a Jupyter Notebook

Appendix A: Overview of the Lisp Programming Language

Appendix B: Resources and Community

Index.

Notes:

Description based on publisher supplied metadata and other sources.

Description based on print version record.

Other Format:

Print version: Herman, Erik L. AI Revealed

ISBN:

9781501520679

OCLC:

1472986459