College of Information Science and Technology,Preface,Course Description: This course introduces the fundamental principles and practical aspects of neural networks, focusing on the feedforward neural network, feedback neural network, hybrid intelligent system based on fuzzy-logic systems and genetic algorithm, and applications in modeling, simulation, control, fault diagnosis, information processing, associative memory and optimization computing.,1. Zurada Jacek MIntroduction to Artificial Neural System West Publishing Company, New York, 1992 2. D. R. Baughman, Y. A. Liu Neural Networks in Bioprocessing and Chemical Engineering Virginia Polytechnic Institute and State University, Blacksburg, 1992 3. Nils J. Nilsson(Staford University). Artificial Intelligence: A New Synthesis. Morgan Kaufmann, 1998 Martin T. Hagan(Oklahoma State University). Neural Network Design. Mark H. Beale(MHB, Inc.) ITP, 1996 Simon Haykin(McMaster University). Neural Network: A Comprehensive Foundation, 2E. Prentice Hall, 1999 Jiawei Han, Micheline Kamber. Data Mining: Concepts and Techniques. Morgan Kaufmann, 2000 7. 袁曾任人工神经元网络及其应用，清华大学出版社，2000 8. 孙增圻. 智能控制理论与技术，清华大学出版社，1997 9. 李士勇. 模糊控制-神经控制和智能控制论，哈尔滨工业大学出版社，1998,Reference,Bio-Intelligence,Machine Intelligence,Evolutionary Programming,Evolutionary Strategy,Genetic Algorithm,Evolutionary Computation,Fuzzy System,Artificial Neural Network,Computation Intelligence,Artificial Intelligence,Rough Set,Intelligent System,Introduction to Intelligent System,. Artificial Intelligent,Artificial intelligence is the part of computer science concerned with designing intelligent computer systems, that is, systems that exhibit characteristics we associate with intelligence in human behavior.,Definition of AI,The goal of AI from the definition,to make computers “think”, to make computers solve problems requiring human intelligence.,Another definition of AI,Artificial intelligence is the branch of computer science dealing with symbolic, non-algorithm methods of problem solving.,Two aspects of AI-based methods for problem-solving,1. AI does not use an algorithm. 2. AI involves symbolic processing.,major AI-based technologies,Expert system,Neural networks,Fuzzy-logic systems,Genetic Algorithms,Rough Set,New,B. Expert System, Neural Networks, and Fuzzy-Logic System,A expert system is a computer program that uses high-quality, in-depth, knowledge to solve complex and advanced problems typically requiring human experts.,Expert systems operate symbolically, on a macroscopic scale, processing non-numerical symbols and names.,A neural network is a computing system made up of a number of simple, highly interconnected nodes or processing elements, which process information by its dynamic state response to external inputs.,The goal of a neural network is to map a set of input patterns onto a corresponding set of output patterns.,Neural networks use subsymbolic processing, characterized by microscopic interaction that eventually manifest themselves as macroscopic, symbolic, intelligent behavior.,Fuzzy-Logic allows us to mesh a quantitative approach with the qualitative representation. It provides a way to quantify certain qualifiers such as approximately, often, rarely, several, few, and very.,To use fuzzy logic, we first need a fuzzy set. In a fuzzy set, the transition from membership to non-membership is not well-defined. We quantify the degree of membership with values between 0(not a member) and 1(definitely a member).,Expert Network,Fuzzy Network,Neural-Fuzzy Networks for Expert Systems,neural network,fuzzifier,expert system,defuzzifier,Numeric values,Fuzzy values,Fuzzy values,Numeric values,Heuristic Programming Expert System Knowledge Engineering Pattern Recognition Natural Language Understanding Theorem Providing Machine Learning Artificial Neural Network Fuzzy Logic Intelligent Robot,AI Features or Functions,Self Adaptation Self Learning Self Recognition Self Stabilization Self Turning Self Coordination Self Organization Self Diagnosis Self Repairing Self Reproduction,AI Methods,Rough Set,Intelligent Control Intelligent Regulation Intelligent Management Intelligent Decision-Making Intelligent Instrument Intelligent Machine Intelligent Communication Intelligent Network Intelligent Interface Intelligent Monitor,Intelligent Diagnosis Intelligent Dispatch Intelligent Operation Intelligent Software Intelligent Robot Intelligent Automation Intelligent Computer Intelligent Database Intelligent Agent Intelligent Housing Colony,Intelligent Applications,Intelligent Control,Intelligent Control,1.1 ANN Development History,1.2 Basic Principle of ANN,1.3 Properties of Neural Networks,1.4 Potential Applications of Neural Networks,Chapter 1 Introduction,1.1 ANN Development History,1943 MP model ( McCulloch and Pitts),1944 Hebb learning rule,Wij=aSiSj a0,1957 Perceptron (Rosenblatt),1962 Adaline (Adaptive linear element) (Widrow),1969 Book “Perceptron”