Artificial Intelligence – Theory and Practice

Author: Gu Guochang
Publisher:
Publish Date: 2004-06-01
Features: This book emphasizes the importance of expression in core chapters on logic, search, and learning. Compared to most introductory textbooks, it introduces more formal discussions on artificial intelligence, as reflected in its focus on syntax and semantic logic, as well as in the coverage of computational complexity of AI algorithms. New computational learning theory results are included as supplementary materials to illustrate various techniques ranging from decision trees to neural networks. The book provides examples of robots and software automation (software robots) that can serve as teaching cases in real-world AI applications, while also extensively introducing other examples to highlight the potential and diversity of AI applications. The chapters on natural language processing, planning, uncertainty, and vision integrate existing methods, summarize challenging areas, and outline technical development prospects for further research. The book does not aim to cover all aspects of AI technology, merely mentioning topics such as qualitative reasoning in physical systems and analogical reasoning in passing, while giving more attention to other subjects than traditional textbooks. It delves into learning, planning, and probabilistic reasoning in depth to reflect their growing importance in the field. The chapter on vision (Chapter 9) addresses topics crucial for demonstrating the role of perception in intelligent understanding and the development of artificial systems (engaging with the world in practical and interesting ways). This is a textbook meticulously written by three senior AI experts, explaining both the fundamental theories and practical applications of artificial intelligence. It introduces new research findings on the expression and computational challenges emerging in the development of machine intelligence systems, while also discussing practical issues involved in system implementation. The authors explore traditional symbolic reasoning techniques for solving learning, planning, and uncertainty problems, such as deductive reasoning and decision trees, and introduce new technologies like neural networks and probabilistic reasoning. Important algorithms mentioned in each chapter are accompanied by their LISP source code implementations at the end of the chapter for reference during experimentation. Additionally, the book provides rich examples of AI application systems. This textbook is suitable for AI courses in computer science, control engineering, mechatronics, mathematics, and other related disciplines at universities and colleges, as well as for researchers and engineering professionals engaged in AI research and applications.