This book provides a complete introduction to Artificial Intelligence, covering foundational computational technologies, mathematical principles, philosophical considerations, and engineering disciplines essential for understanding AI. Artificial Intelligence: Principles and Practice emphasizes the interdisciplinary nature of AI, integrating insights from psychology, mathematics, neuroscience, and more. The book addresses limitations, ethical issues, and the future promise of AI, emphasizing the importance of ethical considerations in integrating AI into modern society. With a modular design, it offers flexibility for instructors and students to focus on specific components of AI, while also providing a holistic view of the field.
Taking a comprehensive but concise perspective on the major elements of the field; from historical background to design practices, ethical issues and more, Artificial Intelligence: Principles and Practice provides the foundations needed for undergraduate or graduate-level courses. The important design paradigms and approaches to AI are explained in a clear, easy-to-understand manner so that readers will be able to master the algorithms, processes, and methods described.
The principal intellectual and ethical foundations for creating artificially intelligent artifacts are presented in Parts I and VIII. Part I offers the philosophical, mathematical, and engineering basis for our current AI practice. Part VIII presents ethical concerns for the development and use of AI. Part VIII also discusses fundamental limiting factors in the development of AI technology as well as hints at AI's promising future. We recommended that PART I be used to introduce the AI discipline and that Part VIII be discussed after the AI practice materials. Parts II through VII present the three main paradigms of current AI practice: the symbol-based, the neural network or connectionist, and the probabilistic.
Generous use of examples throughout helps illustrate the concepts, and separate end-of-chapter exercises are included. Teaching resources include a solutions manual for the exercises, PowerPoint presentation, and implementations for the algorithms in the book.
Table of contents (27 chapters)
Front Matter
Pages I-XVII
I
Front Matter
Pages 1-2
The Pre-History of Artificial Intelligence
George F. Luger
Pages 3-25
Computing, Representations, and Definitions of Artificial Intelligence
George F. Luger
Pages 27-49
II
Front Matter
Pages 51-52
The State Space, Finite State Machines, and Artificial Life
George F. Luger
Pages 53-72
Searching the State Space
George F. Luger
Pages 73-95
Heuristic Search
George F. Luger
Pages 97-123
Heuristics: 2-Person Games and Theoretical Constraints
George F. Luger
Pages 125-147
III
Front Matter
Pages 149-150
Introduction to the Propositional and Predicate Calculi
George F. Luger
Pages 151-170
The Predicate Calculus and Unification
George F. Luger
Pages 171-190
Resolution: Reasoning with the Propositional and Predicate Calculi
George F. Luger
Pages 191-220
IV
Front Matter
Pages 221-222
Download chapter PDF
The Production System Representation and Search Engine
George F. Luger
Pages 223-242
Advanced Applications of Symbol-Based AI: Planning and Learning
George F. Luger
Pages 243-272
Uncertain Reasoning: Symbol Based
George F. Luger
Pages 273-296
V
Front Matter
Pages 297-298
Download chapter PDF
Introduction to Association-Based Knowledge Representations
George F. Luger
Pages 299-319
Association-Based Representations: Frames, Conceptual Graphs, WordNet, and FrameNet
George F. Luger
Pages 321-339
An Introduction to Neural Networks
George F. Luger
Pages 345-361
The Delta Rule, Backpropagation, and Matrix Representations
George F. Luger
Pages 363-382
Deep Learning: Introduction and Representations
George F. Luger
Pages 383-408
Building Language Models and Transformers
George F. Luger
Pages 409-439
Alternative Network Architectures: Prototypes and Classifiers
George F. Luger
Pages 441-458
Alternative Network Architectures: Attractor Networks and Memories
George F. Luger
Pages 459-472
VII
Front Matter
Pages 473-474
Download chapter PDF
Counting, the Foundation for Probabilities
George F. Luger
Pages 475-489
Bayes’ Theorem
George F. Luger
Pages 491-506
Bayesian Belief Networks and Observable Markov Models
George F. Luger
Pages 507-523
Hidden Markov and Alternative Probabilistic Models
George F. Luger
Pages 525-546
VIII
Front Matter
Pages 547-549
Artificial Intelligence: User’s Ethical Issues
George F. Luger
Pages 551-572
AI Ethical Issues: From a Social Perspective
George F. Luger
Pages 573-599
AI: Philosophical Perspectives, Current Limitations, and Future Promise
George F. Luger
Pages 601-614
Back Matter
Pages 615-638
