Artificial Intelligence: A Guide to Intelligent Systems, 4th edition

Published by Pearson (September 17, 2024) © 2025

  • Michael Negnevitsky School of Electrical Engineering and Computer Science, University of Tasmania

eTextbook

from$49.94 NZD
  • Easy-to-use search and navigation
  • Add notes and highlights
  • Quizzes and flashcards help streamline study
  • Access online and offline via mobile app
$156.45 NZD
  • A print text (hardcopy or paperback)
  • Free shipping

Title overview

What are the principles behind intelligent systems?

How are they built? What are intelligent systems useful for? How do we choose the right tool for the job?

These questions are answered by Michael Negnevitsky's Artificial Intelligence: A Guide to Intelligent Systems.

Unlike many books on computer intelligence, which use complex computer science terminology and are crowded with complex matrix algebra and differential equations, this text demonstrates that the ideas behind intelligent systems are simple and straightforward. This text assumes little or no programming experience as it tackles topics like expert systems, fuzzy systems, artificial neural networks, evolutionary computation, knowledge engineering, and data mining.

New to this edition

  • A new chapter on deep learning and convolutional neural networks examines different architectures of convolutional networks and identifies common features of deep neural networks.
  • A new section in the chapter 'Frame-based Systems and Semantic Networks' on semantic networks discusses successful applications of the semantic web like improved data management, enhanced search capabilities, and superior data integration.
  • A new section in the chapter 'Artificial Neural Networks and Machine Learning' introduces the concepts of model-based and model-free reinforcement learning.
  • A new section in the chapter 'Introduction to Intelligent Systems' on generative AI explores chatbots like Alexa, Siri, and ChatGPT.
  • Real-world case studies set theory into context. Two of the case studies are new: one focuses on image recognition using a convolutional neural network, while the other explains how to find the optimum of an unknown function using particle swarm optimisation.

Key features

What is Pearson eTextbook?

  • A lightweight, lower cost, digital replacement for a print textbook
  • A digital reading experience that takes advantage of digital capabilities to better deliver content to learners
  • Accessible on any device via browser and Pearson+ mobile app

Why choose Pearson eTextbook?

  • Students can study in a flash with instant, ready-made Pearson flashcards or easily create their own
  • Enhanced search with a minimum of three characters allows students to search media, images, key terms and their own notes
  • Pearson eTextbook embed videos and other interactives directly in the text to bring concepts to life
  • Pearson eTextbook features clear and engaging content from experienced authors. Each eTextbook is designed to help students reach their potential with a mix of learning features including problem-solving exercises, reflection questions and real-world examples.
  • Pearson eTextbook, optimised for mobile, seamlessly integrates videos and other rich media with the text and gives students access to their textbook anytime, anywhere.

Table of contents

  • 1. Introduction to Intelligent Systems
  • 1.1 Intelligent Machines, or What Machines Can Do
  • 1.2 The History of Artificial Intelligence, or From the 'Dark Ages' to Knowledge-based Systems
  • 1.3 Generative AI
  • 2. Expert Systems
  • 2.1 Introduction, or Knowledge Representation Using Rules
  • 2.2 The Main Players in the Expert System Development Team
  • 2.3 Structure of a Rule-based Expert System
  • 2.4 Fundamental characteristics of an expert system
  • 2.5 Forward Chaining and Backward Chaining Inference Techniques
  • 2.6 MEDIA ADVISOR: A Demonstration Rule-based Expert System
  • 2.7 Conflict Resolution
  • 2.8 Uncertainty Management in Rule-based Expert Systems
  • 2.9 Advantages and Disadvantages of Rule-based Expert systems
  • 3. Fuzzy Systems
  • 3.1 Introduction, or What Is Fuzzy Thinking?
  • 3.2 Fuzzy Sets
  • 3.3 Linguistic Variables and Hedges
  • 3.4 Operations of Fuzzy Sets
  • 3.6 Fuzzy Inference
  • 3.7 Building a Fuzzy Expert System
  • 4. Frame-based Systems and Semantic Networks
  • 4.1 Introduction, or What Is a Frame?
  • 4.2 Frames as a Knowledge Representation Technique
  • 4.3 Inheritance in Frame-based Systems
  • 4.4 Methods and Demons
  • 4.5 Interaction of Frames and Rules
  • 4.6 Buy Smart: A Frame-based Expert System
  • 4.7 The Web of Data
  • 4.8 RDF - Resource Description Framework and RDF Triples
  • 4.9 Turtle, RDF Schema and OWL
  • 4.10 Querying the Semantic Web with SPARQL
  • 5. Artificial Neural Networks
  • 5.1 Introduction, or How the Brain Works
  • 5.2 The Neuron as a Simple Computing Element
  • 5.3 The Perceptron
  • 5.4 Multilayer Neural Networks
  • 5.5 Accelerated Learning in Multilayer Neural Networks
  • 5.6 The Hopfield Network
  • 5.7 Bidirectional Associative Memory
  • 5.8 Self-organising Neural Networks
  • 5.9 Reinforcement Learning
  • 6. Deep Learning and Convolutional Neural Networks
  • 6.1 Introduction, or How 'Deep' Is a Deep Neural Network?
  • 6.2 Image Recognition or How Machines See the World
  • 6.3 Convolution in Machine Learning
  • 6.4 Activation Functions in Deep Neural Networks
  • 6.5 Convolutional Neural Networks
  • 6.6 Back-propagation Learning in Convolutional Networks
  • 6.7 Batch Normalisation
  • 7. Evolutionary Computation
  • 7.1 Introduction, or Can Evolution Be Intelligent?
  • 7.2 Simulation of Natural Evolution
  • 7.3 Genetic Algorithms
  • 7.4 Why Genetic Algorithms Work
  • 7.5 Maintenance Scheduling with Genetic Algorithms
  • 7.6 Genetic Programming
  • 7.7 Evolution Strategies
  • 7.8 Ant Colony Optimisation
  • 7.9 Particle Swarm Optimisation
  • 8. Hybrid Intelligent Systems
  • 8.1 Introduction, or How to Combine German Mechanics with Italian Love
  • 8.2 Neural Expert Systems
  • 8.3 Neuro-Fuzzy Systems
  • 8.4 ANFIS: Adaptive Neuro-Fuzzy Inference System
  • 8.5 Evolutionary Neural Networks
  • 8.6 Fuzzy Evolutionary Systems
  • 9. Knowledge Engineering
  • 9.1 Introduction, or What Is Knowledge Engineering?
  • 9.2 Will an Expert System Work for My Problem?
  • 9.3 Will a Fuzzy Expert System Work for My Problem?
  • 9.4 Will a Neural Network Work for My Problem?
  • 9.5 Will a Deep Neural Network Work for My Problem?
  • 9.6 Will Genetic Algorithms Work for My Problem?
  • 9.7 Will Particle Swarm Optimisation Work for My Problem?
  • 9.8 Will a Hybrid Intelligent System Work for My Problem?
  • 10. Data Mining and Knowledge Discovery
  • 10.1 Introduction, or What Is Data Mining?
  • 10.2 Statistical Methods and Data Visualisation
  • 10.3 Principal Components Analysis
  • 10.4 Relational Databases and Database Queries
  • 10.5 The Data Warehouse and Multidimensional Data Analysis
  • 10.6 Decision Trees
  • 10.7 Association Rules and Market Basket Analysis
  • Glossary
  • Index

Author bios

Dr Michael Negnevitsky is a Professor in Electrical Engineering and Computer Science at the University of Tasmania, Australia. This text has been developed from his lectures to undergraduates. Educated as an electrical engineer, Dr Negnevitsky's many interests include artificial intelligence and soft computing. His research involves the development and application of intelligent systems in electrical engineering, process control, and environmental engineering. He has authored and co-authored over 300 research publications including numerous journal articles, four patents for inventions, and two books.

Need help?Get in touch

Pearson eText

Extend learning beyond the classroom. Pearson eText is an easy-to-use digital textbook. It lets students customise how they study and learn with enhanced search and the ability to create flashcards, highlight and add notes all in one place. The mobile app lets students learn wherever life takes them, offline or online.

Video
Play
Privacy and cookies
By watching, you agree Pearson can share your viewership data for marketing and analytics for one year, revocable upon changing cookie preferences. Disabling cookies may affect video functionality. More info...

Video transcript (PDF | 16KB) 

Pearson eTextbook: What’s on the inside just might surprise you

They say you can’t judge a book by its cover. It’s the same with your students. Meet each one right where they are with an engaging, interactive, personalized learning experience that goes beyond the textbook to fit any schedule, any budget, and any lifestyle.