Contemporary Artificial Intelligence

"A thorough introduction to artificial intelligence (AI), this text provides a comprehensive and in-depth overview of the key concepts and techniques in AI. It also discusses the various areas and successes of the rational and emergent software approaches to AI. Throughout the text, theory is introduced via examples, giving readers the foundation to solve problems with logic that they can use later in AI-related research and other domains. The author also covers algorithms in sufficient detail, allowing readers to readily understand and implement them"--

Richard E. Neapolitan is a professor of computer science at Northeastern Illinois University. Dr. Neapolitan has published in prestigious journals related to reasoning under uncertainty and has authored five books: Probabilistic Reasoning in Expert Systems, Learning Bayesian Networks, Foundations of Algorithms, Probabilistic Methods for Financial and Marketing Informatics, and Probabilistic Methods for Bioinformatics. His research interests include probability and statistics, expert systems, cognitive science, and applications of probabilistic modeling to fields such as medicine, biology, and finance.

Xia Jiang is an assistant professor in the Department of Biomedical Informatics at the University of Pittsburgh. Dr. Jiang co-authored Probabilistic Methods for Financial and Marketing Informatics. Her current research focuses on developing novel algorithms/systems that improve the computational efficiency of large data analysis and network modeling of cancer genome data.

Introduction
What is Artificial Intelligence?
Rational Artificial Intelligence
Emergent Intelligence
Natural Language Understanding


LOGICAL INTELLIGENCE
Propositional Logic
Syntax
Semantics
Inference
Forward chaining
Backward chaining
Logic-based agents


Predicate First-Order Logic
Syntax
Semantics
Inference
Forward chaining
Backward chaining
Logic-based agents


Knowledge Representation
Ontologies
Ontology Components


Planning
The Planning Problem
Forward Chaining State Space Search
Backward Chaining State Space Search


Learning
Types of Learning
Learning Decision Trees
Inductive Logic


PROBABILISTIC INTELLIGENCE
Probability
Fundamentals of Probability
Bayesian versus Frequentist Probability
Bayes’ Theorem


Bayesian Networks
Properties of Bayesian networks
Inference in Bayesian networks
Dynamic Bayesian networks


Influence Diagrams
Decision trees
Representing Problems with Influence Diagrams
Solving Influence Diagrams
Dynamic Influence Diagrams


Learning Bayesian Networks
Learning Bayesian Network Parameters
Learning Bayesian Network Structure
Learning with Hidden Variables


Related Machine Learning Techniques
Neural Networks
Support Vector Machines


EMERGENT INTELLIGENCE
Agent-Based Models
Intelligent Autonomous Agents
The Single-Agent Model
The Multi-Agent Model


Multi-Agent Systems
Swarm Intelligence
Swarm Robot Meta-heuristics
Applications to Solving NP-Hard Problems


Evolutionary Computation
Evolutionary Programming
Evolutionary Strategies
Genetic Algorithms
Genetic Programming


NATURAL LANGUAGE PROCESSING
Deterministic Language Models
Linguistics Foundation
Context Free Grammars
n-Gram Models
Parsing
Applications


Probabilistic Language Models
Statistical Inference
Markov Models
Probabilistic Context Free Grammars and Parsing
Applications