Artificial Intelligence: Principles and Practice

George Luger is Professor Emeritus of Computer Science at the University of New Mexico. Dr. Luger was also a Professor in the Psychology and Linguistics Departments, reflecting his interdisciplinary interests in Cognitive Science and Computational Linguistics.The National Science Foundation, NATO, the British Royal Society, NASA, the Smithsonian Institution, NIH, the Departments of Defense, Energy and Transportation, NIH, and other government agencies have supported George Luger's research. He has worked with the Los Alamos and Sandia National Laboratories and for numerous companies.  Currently, his consulting is in the design of natural language web agents and deep learning technologies that analyze information in very large collections of data. Dr. Luger is the author of Artificial Intelligence: Structures and Strategies for Complex Problem Solving (Addison-Wesley, 2009), now in its Sixth Edition, and Knowing Our World (Springer, 2021).

• The Pre-History of Artificial Intelligence.- Computing, Representations, and Definitions of Artificial Intelligence.- The State Space, Finite State Machines, and Artificial Life.- Searching the State Space.- Heuristic Search.- Heuristics: 2-Person Games and Theoretical Constraints.- Introduction to the Propositional and Predicate Calculi.- The Predicate Calculus and Unification.- Resolution: Reasoning with the Propositional and Predicate Calculi.- The Production System Representation and Search Engine.- Advanced Applications of Symbol-Based Reasoning.- Uncertain Reasoning: Symbol-Based.- Introduction to Association-Based Knowledge Representations.- Association-Based Representations: Frames, Conceptual Graphs, WordNet, and FrameNet.- An Introduction to Neural Networks.- The Delta Rule, Backpropagation, and Matrix Representations.- Deep Learning: Introduction and Representations.- Building Language Models and Transformers.- Alternative Network Architectures: Prototypes and Classifiers.- Alternative Network Architectures: Attractor Networks and Memories.- Counting, the Foundation of Probabilities.- Bayes’ Theorem.- Bayesian Belief Networks and Observable Markov Models.- Hidden Markov and Alternative Probabilistic Models.- Artificial Intelligence: User-Focused Ethical Issues.- AI Ethical Issues: From the Developers’ Perspective.- Artificial Intelligence: Current Limitations and Future Promise.