This book was originally titled “Fundamentals of the New Artificial Intelligence: Beyond Traditional Paradigms.” I have changed the subtitle to better represent the contents of the book. The basic philosophy of the original version has been kept in the new edition. That is, the book covers the most essential and widely employed material in each area, particularly the material important for real-world applications. Our goal is not to cover every latest progress in the fields, nor to discuss every detail of various techniques that have been developed. New sections/subsections added in this edition are: Simulated Annealing (Section 3.7), Boltzmann Machines (Section 3.8) and Extended Fuzzy if-then Rules Tables (Sub-section 5.5.3). Also, numerous changes and typographical corrections have been made throughout the manuscript. The Preface to the first edition follows.
General scope of the book
Artificial intelligence (AI) as a field has undergone rapid growth in diversification and practicality. For the past few decades, the repertoire of AI techniques has evolved and expanded. Scores of newer fields have been added to the traditional symbolic AI. Symbolic AI covers areas such as knowledge-based systems, logical reasoning, symbolic machine learning, search techniques, and natural language processing. The newer fields include neural networks, genetic algorithms or evolutionary computing, fuzzy systems, rough set theory, and chaotic systems. The traditional symbolic AI has been taught as the standard AI course, and there are many books that deal with this aspect. The topics in the newer areas are often taught individually as special courses, that is, one course for neural networks, another course for fuzzy systems, and so on. Given the importance of these fields together with the time constraints in most undergraduate and graduate computer science curricula, a single book covering the areas at an advanced level is desirable. This book is an answer to that need.