Bibliographic record and links to related information available from the Library of Congress catalog.
Note: Contents data are machine generated based on pre-publication provided by the publisher. Contents may have variations from the printed book or be incomplete or contain other coding.
Chapter 1 The 50 - year History of Artificial Intelligence 1 1.1 Departure from Dartmouth Symposium 1 1.1.1 Communications between Different Disciplines 1 1.1.2 Development and Growth 3 1.2 Expected Goals as Time Goes on 4 1.2.1 Turing Test 4 1.2.2 Machine Theorem Proof 5 1.2.3 Rivalry between Kasparov and Deep Blue 6 1.2.4 Thinking Machine 7 1.2.5 Artificial Life 8 1.3 AI Achievements in 50 years 9 1.3.1 Pattern Recognition 10 1.3.2 Knowledge Engineering 12 1.3.3 Robotics 14 1.4 Major Development of AI in the Information Age 15 1.4.1 Impacts of AI Technology on the Whole Society 15 1.4.2 From World Wide Web to Intelligent Grid 16 1.4.3 From Data to Knowledge 17 1.5 The Cross Trend between AI, Brain Science and Cognitive Science 18 1.5.1 The Influence of Brain Science to AI 18 1.5.2 The Influence of Cognitive Science to AI 21 1.5.3 Coming Breakthroughs Caused by Interdisciplines 22 Chapter 2 Methodologies of AI 1 2.1 Symbolism Methodology 1 2.1.1 Birth and Development of Symbolism 1 2.1.2 Predicate Calculus and Resolution Principle 5 2.1.3 Logic Programming Language 7 2.1.4 Expert System 9 2.2 Connectionism Methodology 11 2.2.1 Birth and Development of Connectionism 12 2.2.2 Strategy and Technical Characteristics of Connectionism 13 2.2.3 Hopfield Neural Network Model 16 2.2.4 Back-Propagation Neural Network Model 17 2.3 Behaviorism Methodology 19 2.3.1 Birth and Development of Behaviorism 19 2.3.2 Robot Control 20 2.3.3 Intelligent Control 21 2.4 Reflection on Methodologies 23 Chapter 3 On Uncertainties of Knowledge 1 3.1 On Randomness 1 3.1.1 The Objectivity of Randomness 1 3.1.2 The Beauty of Randomness 4 3.2 On Fuzziness 6 3.2.1 The Objectivity of Fuzziness 7 3.2.2 The Beauty of Fuzziness 9 3.3 Uncertainties in Natural Languages 11 3.3.1 Languages as the Carrier of Human's Knowledge 11 3.3.2 Uncertainties in Languages 12 3.4 Uncertainties in Commonsense Knowledge 15 3.4.1 Common Understanding about Common Sense 15 3.4.2 Relativity of Commonsense Knowledge 17 3.5 Other Uncertainties of Knowledge 18 3.5.1 Incompleteness of Knowledge 19 3.5.2 Incoordination of Knowledge 20 3.5.3 Impermanence of Knowledge 21 Chapter 4 Mathematical Foundation of AI with Uncertainty 1 4.1 Probability Theory 1 4.1.1 Bayes Theorem 2 4.1.2 Probability Distribution Function 6 4.1.3 Normal Distribution 8 4.1.4 Large Number Laws and Central Limit Theorem 11 4.1.5 Power Law Distribution 14 4.1.6 Entropy 16 4.2 Fuzzy Set Theory 17 4.2.1 Membership Degree and Membership Function 18 4.2.2 Decomposition Theorem and Expanded Principle 20 4.2.3 Fuzzy Relation 22 4.2.4 Possibility Measure 23 4.3 Rough Set Theory 24 4.3.1 Imprecise Category and Rough Set 25 4.3.2 Characteristics of Rough Set 28 4.3.3 Rough Relations 29 4.4 Chaos and Fractal 32 4.4.1 Basic Characteristics of Chaos 33 4.4.2 Strange Attractors of Chaos 36 4.4.3 Geometric Characteristics of Chaos and Fractal 38 4.5 Kernel Functions and Principal Curves 38 4.5.1 Kernel Functions 39 4.5.2 Support Vector Machine 42 4.5.3 Principal Curves 45 Chapter 5 Qualitative and Quantitative Transform Model - Cloud Model 1 5.1 Perspectives in the Study of AI with Uncertainty 1 5.1.1 Multiple Perspectives in the Study of Human¿s Intelligence 1 5.1.2 Importance of Concepts in Natural Languages 4 5.1.3 Relationship between Randomness and Fuzziness in a Concept 5 5.2 Representing Concepts Using Cloud Models 7 5.2.1 Cloud and Cloud Drop 7 5.2.2 Numerical Characteristics of Cloud 9 5.2.3 Types of Cloud Model 10 5.3 Normal Cloud Generator 11 5.3.1 Forward Cloud Generator 11 5.3.2 Contributions of Cloud Drops to a Concept 16 5.3.3 Understanding Lunar Calendar¿s Solar Terms through Cloud Models 17 5.3.4 Backward Cloud Generator 18 5.3.5 Precision Analysis of Backward Cloud Generator 24 5.3.6 More on understanding Normal Cloud Model 26 5.4 Mathematical Properties of Normal Cloud 29 5.4.1 Statistical Analysis of the Cloud Drops¿ Distribution 29 5.4.2 Statistical Analysis of the Cloud Drops¿ Certainty Degree 31 5.4.3 Expectation Curves of Normal Cloud 33 5.5 On the Pervasiveness of the Normal Cloud Model 34 5.5.1 Pervasiveness of Normal Distribution 35 5.5.2 Pervasiveness of Bell Membership Function 36 5.5.3 Significance of Normal Cloud 38 Chapter 6 Discovering Knowledge with Uncertainty through Methodologies in Physics 1 6.1 From Perception of Physical World to Perception of Human Self 1 6.1.1 Expressing Concepts by Using Atom Models 2 6.1.2 Describing Interaction between Objects by Using Field 3 6.1.3 Describing Hierarchical Structure of Knowledge by Using Granularity 5 6.2 Data Field 7 6.2.1 From Physical Field to Data Field 7 6.2.2 Potential Field and Force Field of Data 10 6.2.3 Influence Coefficient Optimization of Field Function 20 6.2.4 Data Field and Visual Thinking Simulation 23 6.3 Uncertainty in Concept Hierarchy 28 6.3.1 Discretization of Continuous Data 30 6.3.2 Virtual Pan Concept Tree 36 6.3.3 Cross-Layer Strategy and Algorithms 37 6.4 Knowledge Discovery State Space 46 6.4.1 Three Kinds of State Spaces 47 6.4.2 State Space Transformation 48 6.4.3 Major Operations in State Space Transformation 50 Chapter 7 Data Mining for Discovering Knowledge with Uncertainty 1 7.1 Uncertainty in Data Mining 1 7.1.1 Data Mining and Knowledge Discovery 1 7.1.2 Uncertainty in Data Mining Process 3 7.1.3 Uncertainty in Discovered Knowledge 5 7.2 Classification and Clustering with Uncertainty 6 7.2.1 Cloud Classification 7 7.2.2 Clustering Based on Data Field 15 7.2.3 Examination and Discovery of Offlets Based on Data Field 41 7.3 Discovery of Association Rules with Uncertainty 47 7.3.1 Reconsideration on the Traditional Association Rules 47 7.3.2 Association Rule Mining and Forecasting 51 7.4 Time Series Data Mining and Forecasting 58 7.4.1 Time Series Data Mining Based on Cloud Models 60 7.4.2 Stock Data Forecasting 62 Chapter 8 Reasoning and Control of Qualitative Knowledge 1 8.1 Qualitative Rule Construction by Cloud 1 8.1.1 Precondition Cloud Generator and Postcondition Cloud Generator 2 8.1.2 Rule Generator 4 8.1.3 From Cases to Rule Generation 8 8.2 Qualitative Control Mechanism 9 8.2.1 Fuzzy, Probability, and Cloud Control Methods 9 8.2.2 Theoretic Explanation of Mamdani Fuzzy Control Method 19 8.3 Inverted Pendulum - an Example of Intelligent Control with Uncertainty 21 8.3.1 Inverted Pendulum System and Its Control 21 8.3.2 Inverted Pendulum Qualitative Control Mechanism 22 8.3.3 Cloud Control Policy of Triple Link Inverted Pendulum 25 8.3.4 Balancing Patterns of an Inverted Pendulum 36 Chapter 9 A New Direction of AI with Uncertainty 1 9.1 Computing with Words 2 9.2 Study on Cognitive Physics 7 9.2.1 Extension of Cloud Model 7 9.2.2 Dynamic Data Field 12 9.3 Complex Networks with Small World and Scale-Free Models 15 9.3.1 Regularity of Uncertainty in Complex Network 16 9.3.2 Scale-Free Networks Generation 20 9.3.3 Applications of Data Field Theory to Networked Intelligence 24 9.4 Long Way to Go for AI with Uncertainty 25 9.4.1 Limitations of Cognitive Physics Methodology 25 9.4.2 Divergences from Daniel, the Nobel Economic Prize Winner 26
Library of Congress Subject Headings for this publication:
Artificial intelligence.
Uncertainty (Information theory).