Artificial Intelligence: From Beginning to Date
- Length: 576 pages
- Edition: 1
- Language: English
- Publisher: World Scientific Pub Co Inc
- Publication Date: 2021-06-04
- ISBN-10: 9811223718
- ISBN-13: 9789811223716
- Sales Rank: #9576086 (See Top 100 Books)
This is the English edition monograph developed and updated from China’s best-selling and award-winning book on Artificial Intelligence. It covers the foundations as well as the latest developments of Artificial Intelligence in a comprehensive and systematic manner and can be used as a valuable guide for students and researchers. A wide range of topics in artificial intelligence are covered in this book with three distinct features. First of all, the book is in a comprehensive system, covering the core technology of artificial intelligence, including the basic theories and techniques of “”traditional”” artificial intelligence, and the basic principles and methods of computational intelligence. Secondly, the book focuses on innovation, focusing on advanced learning methods for machine learning and deep learning techniques and other artificial intelligence that have been widely used in recent years. Thirdly, the theory and practice of the book are highly integrated. There are theories, techniques and methods, as well as many application examples, which will help readers to understand the artificial intelligence theory and its application development.
Cover Page Title Page Copyright Page Contents Foreword List of Tables List of Figures About the Authors Chapter 1. Introduction 1.1 Definition and Development of Artificial Intelligence 1.1.1 Definition of artificial intelligence 1.1.2 Origin and development of artificial intelligence 1.2 Classification of Artificial Intelligence Systems 1.3 Research Objectives and Contents of Artificial Intelligence 1.3.1 Research objectives of artificial intelligence 1.3.2 Research and application fields of artificial intelligence 1.4 Core Elements of Artificial Intelligence 1.5 Outline of the Book References Part 1: Knowledge-based Artificial Intelligence Chapter 2. Knowledge Representation 2.1 State Space Representation 2.1.1 Problem state space description 2.1.2 Graph theory terminology and graphic method 2.1.3 Problem reduction representation 2.2 Knowledge Base 2.2.1 Definition and characteristics of knowledge base 2.2.2 Design and application of knowledge base 2.3 Ontology 2.3.1 Concept and definition of ontology 2.3.2 Composition and classification of ontology 2.3.3 Ontology modeling 2.4 Semantic Network Representation 2.4.1 Composition and characteristics of the semantic network 2.4.2 Representation of a binary semantic network 2.4.3 Representation of a multi-element semantic network 2.4.4 Inference process of a semantic network 2.5 Knowledge Graph 2.5.1 Definition and architecture of knowledge graph 2.5.2 Key technologies of knowledge graph 2.6 Frame Representation 2.6.1 Frame composition 2.6.2 Frame reasoning 2.7 Predicate Logic Representation 2.7.1 Predicate calculus 2.7.2 Predicate formula 2.8 Summary References Chapter 3. Knowledge Search and Reasoning 3.1 Graph Search Strategy 3.2 Blind Search 3.2.1 Breadth-first search 3.2.2 Depth-first search 3.2.3 Uniform cost search 3.3 Heuristic Search 3.3.1 Heuristic search strategy and valuation function 3.3.2 Ordered search 3.3.3 Algorithm A* 3.4 Resolution Principles 3.4.1 Extraction of the clause set 3.4.2 Rules of resolution reasoning 3.4.3 Solving process of resolution refutation 3.5 Rule Deduction System 3.5.1 Rule forward deduction system 3.5.2 Rule reverse deduction system 3.5.3 Rule bidirectional deduction system 3.6 Reasoning with Uncertainty 3.6.1 Representation and measurement of uncertainty 3.6.2 Algorithm of uncertainty 3.7 Probabilistic Reasoning 3.7.1 Basic properties and computing formulas of probability 3.7.2 Method of probabilistic reasoning 3.8 Subjective Bayesian Method 3.8.1 Representation about knowledge uncertainty 3.8.2 Representation about evidence uncertainty 3.8.3 Reasoning procedure of the subjective Bayesian method 3.9 Summary References Chapter 4. Knowledge-Based Machine Learning 4.1 Definition and Development of Machine Learning 4.1.1 Definition of machine learning 4.1.2 Development history of machine learning 4.2 Main Strategies and Basic Structure of Machine Learning 4.2.1 Main strategies of machine learning 4.2.2 Basic structure of the machine learning system 4.3 Inductive Learning 4.3.1 Modes and rules of inductive learning 4.3.2 Example-based learning 4.3.3 Learning from observation and discovery 4.4 Learning by Explanation 4.4.1 Process and algorithm of explanatory learning 4.4.2 Example of explanatory learning 4.5 Learning by Analogy 4.5.1 Analogy inference and form of analogy learning 4.5.2 Process and research type of analogy learning 4.6 Reinforcement Learning 4.6.1 Overview of reinforcement learning 4.6.2 Q-learning 4.7 Summary References Part 2: Data-based Artificial Intelligence Chapter 5. Neural Computation 5.1 Overview of Computational Intelligence 5.2 Research Advances in Artificial Neural Networks 5.3 Basic Structure of Artificial Neural Network 5.3.1 Neuron and its characteristics 5.3.2 Basic characteristics and structure of ANN 5.3.3 Main learning algorithms of ANN 5.4 Deep Neural Networks 5.4.1 Brief introduction to DNNs 5.4.2 Common models of deep neural network 5.4.3 Structure analysis of convolutional neural network 5.5 Summary References Chapter 6. Evolutionary Computation 6.1 Evolutionary Algorithms (EAs) 6.1.1 The basic idea of EAs 6.1.2 The research areas and paradigms of EAs 6.2 Solving Constrained Optimization Problems by Evolutionary Algorithms 6.2.1 Constrained optimization problems (COPs) and constraint-handling techniques 6.2.2 Further analysis of the methods based on multi-objective optimization techniques 6.2.3 A multi-objective optimization-based EA for COPs 6.3 Solving Multi-objective Optimization Problems by Evolutionary Algorithms 6.3.1 Multi-objective optimization problems (MOPs) and the related definitions 6.3.2 A regularity model-based multi-objective estimation of distribution algorithm (RM-MEDA) 6.3.3 The drawback of modeling in RM-MEDA 6.3.4 An improved RM-MEDA (IRM-MEDA) 6.3.5 Experimental study 6.4 An Application of EA for Descriptor Selection in Quantitative Structure–Activity/Property Relationship (QSAR/QSPR) 6.4.1 Background 6.4.2 Weighted sampling PSO-PLS (WS-PSO-PLS) 6.4.3 Experimental study 6.5 Summary References Chapter 7. Data-based Machine Learning 7.1 Linear Regression 7.2 Decision Tree 7.2.1 Decision tree model and learning 7.2.2 Feature selection 7.2.3 Generation algorithm of decision trees 7.2.4 Pruning of decision trees 7.3 Support Vector Machine 7.3.1 Intervals and support vectors 7.3.2 Duality problem 7.3.3 Soft interval and regularization 7.3.4 Kernel function 7.4 Integrated Learning 7.4.1 Random forest 7.4.2 Adaboost algorithm 7.5 Clustering 7.5.1 Distance calculation 7.5.2 The k-means clustering 7.5.3 Sample description 7.6 Deep Learning 7.6.1 Definition and characteristics of deep learning 7.6.2 Deep learning model training and optimization 7.6.3 Applications of deep learning 7.7 Summary References Part 3: Application Examples of Artificial Intelligence Chapter 8. Expert System 8.1 Overview of Expert Systems 8.1.1 Definition, characteristics, and types of expert systems 8.1.2 Structure and construction steps of expert systems 8.2 Rule-based Expert System 8.2.1 Working model and architecture of a rule-based expert system 8.2.2 Features of a rule-based expert system 8.3 Model-based Expert System 8.3.1 Proposal of a model-based expert system 8.3.2 Expert system based on neural networks 8.4 Web-based Expert System 8.4.1 Structure of the Web-based expert system 8.4.2 Example of a Web-based expert system 8.5 Design of the Expert System 8.6 Expert Systems Based on Machine Learning 8.6.1 Introduction to expert systems based on machine learning 8.6.2 Example of expert systems based on deep learning 8.7 Summary References Chapter 9. Intelligent Planning 9.1 Overview of Intelligent Planning 9.1.1 Concept and function of planning 9.1.2 Classification of planning 9.2 Task Planning 9.2.1 Robot planning in the block world 9.2.2 Task planning based on the resolution principle 9.3 Planning System with Learning Ability 9.3.1 Structure and operation modes of the PULP-I system 9.3.2 World model and planning results of the PULP-I system 9.4 Planning Based on Expert Systems 9.4.1 Structure and planning mechanism of the system 9.4.2 ROPES robot planning system 9.5 Path Planning 9.5.1 Main methods of robot path planning 9.5.2 Development trends of path planning 9.6 Robot Path Planning Based on Ant Colony Algorithm 9.6.1 Introduction to the ant colony optimization algorithm 9.6.2 Path planning based on ant colony algorithm 9.7 Intelligent Planning Based on Machine Learning 9.7.1 Advances in intelligent planning based on machine learning 9.7.2 Autonomous path planning based on deep reinforcement learning for unmanned ships 9.8 Conclusion 9.9 Summary References Chapter 10. Intelligent Perception 10.1 Introduction to Pattern Recognition 10.1.1 What is pattern recognition? 10.1.2 The difference between pattern recognition and machine learning 10.1.3 Research methods of pattern recognition 10.2 Image Analysis and Understanding 10.2.1 Image engineering 10.2.2 Image processing and image analysis 10.2.3 Image understanding 10.3 The Case of Image Understanding Based on Deep Learning: DenseCap 10.4 Basic Principles and Development of Speech Recognition 10.4.1 How does speech recognition work? 10.4.2 Development of speech recognition 10.5 Key Technologies of Speech Recognition 10.5.1 Acoustic feature extraction 10.5.2 Acoustic model 10.5.3 Language model 10.5.4 Search algorithms in speech recognition 10.5.5 Performance evaluation 10.5.6 Outlook of speech recognition technology 10.6 Case of Speech Recognition Based on Deep Learning: Deep Speech 10.7 Summary References Chapter 11. Natural Language Understanding 11.1 Overview of Natural Language Understanding 11.1.1 Language and language understanding 11.1.2 Concept and definitions of natural language processing 11.1.3 Research areas and significance of natural language processing 11.1.4 Basic methods and advances in research on natural language understanding 11.1.5 Levels of the natural language understanding process 11.2 Lexical Analysis 11.3 Syntactic Analysis 11.3.1 Phrase structure grammar 11.3.2 Chomsky’s formal grammar 11.3.3 Transition network 11.3.4 Lexical functional grammar 11.4 Semantic Analysis 11.5 Automatic Understanding of Sentences 11.5.1 Understanding of simple sentences 11.5.2 Understanding of complex sentences 11.6 Corpus Linguistics 11.7 Main Models of Natural Language Understanding Systems 11.8 Natural Language Processing Based on Deep Learning 11.8.1 Overview of deep learning-based natural language processing technologies 11.8.2 Natural language processing example based on deep learning 11.9 Summary References Chapter 12. Prospects of Artificial Intelligence 12.1 The Impact of Artificial Intelligence on Humans 12.1.1 Great benefits of artificial intelligence 12.1.2 Security issues of artificial intelligence 12.2 Deep Fusion of Artificial Intelligence Technology 12.2.1 Fusion of artificial intelligence technology in machine learning 12.2.2 Fusion of AI technology in deep reinforcement learning 12.2.3 Fusion of deep learning and traditional artificial intelligence technology 12.3 Industrialization of Artificial Intelligence 12.3.1 Current status of AI industrialization 12.3.2 Development trend of AI industrialization References Epilogue Index
Donate to keep this site alive
1. Disable the AdBlock plugin. Otherwise, you may not get any links.
2. Solve the CAPTCHA.
3. Click download link.
4. Lead to download server to download.