Introduction to Artificial Neural Networks

Author: Zhang Qinggui
Publisher:
Publish Date: 2004-10-01
Features: This book systematically introduces the basic theories and methods of artificial neural networks. The entire book consists of 10 chapters, which can be divided into four parts: Part I includes Chapters 1 and 2, which describe the foundational knowledge required to learn artificial neural networks, covering topics such as the structure of the brain's nervous system, the working principles of brain neurons, the concept of artificial neural networks, the stability of dynamical systems, and chaos. Part II includes Chapters 3 to 5, which discuss the three essential elements of artificial neural networks: artificial neuron models, the connection methods of artificial neurons, and the training and learning of artificial neural networks. Part III includes Chapters 6 to 9, which focus on four major types of networks: feedforward networks, dynamic networks, competitive networks, and fuzzy networks, with each major type containing several specific network models. Part IV is Chapter 10, which discusses statistical learning theory, with support vector machines as a special case. While emphasizing fundamental theories and systematicity, the book also highlights the latest research findings in the field of artificial neural networks. It is suitable as a graduate textbook for majors such as automatic control, electronic technology, information technology, computer science, and systems engineering in universities, as well as a reference for relevant technical personnel. This book systematically introduces the basic theories and methods of artificial neural networks. The entire book consists of 10 chapters, which can be divided into four parts: Part I includes Chapters 1 and 2, which describe the foundational knowledge required to learn artificial neural networks, covering topics such as the structure of the brain's nervous system, the working principles of brain neurons, the concept of artificial neural networks, the stability of dynamical systems, and chaos. Part II includes Chapters 3 to 5, which discuss the three essential elements of artificial neural networks: artificial neuron models, the connection methods of artificial neurons, and the training and learning of artificial neural networks. Part III includes Chapters 6 to 9, which focus on four major types of networks: feedforward networks, dynamic networks, competitive networks, and fuzzy networks, with each major type containing several specific network models. Part IV is Chapter 10, which discusses statistical learning theory, with support vector machines as a special case. While emphasizing fundamental theories and systematicity, the book also highlights the latest research findings in the field of artificial neural networks. It is suitable as a graduate textbook for majors such as automatic control, electronic technology, information technology, computer science, and systems engineering in universities, as well as a reference for relevant technical personnel.