Recursion Theory for Metamathematics

Pearson’s Artificial Intelligence encompasses a comprehensive text on the fundamental principles and concepts of Artificial Intelligence—a new-age technology that fuels the much-coveted ‘Industry 4.0’. Presented in lucid English, this book covers all the basic concepts, enriched with latest examples. It also discusses all the major components of AI, such as Neural Networks, Natural Language Processing, Reinforcement Learning, Machine Learning, Deep Learning and Computer Vision. The book is a deliberation of classical as well modern AI techniques and related technologies that provides readers with an overall knowledge and understanding of AI in present-day context. About Pearson Title Page Contents Preface About the Book Acknowledgments About the Author 1. Introduction to Artificial Intelligence 1.1 What is Artificial Intelligence? 1.1.1 How Does AI Work? 1.1.2 Advantages and Disadvantages of Artificial Intelligence 1.2 History of Artificial Intelligence 1.3 Types of Artificial Intelligence 1.3.1 Weak AI 1.3.2 Strong AI 1.3.3 Reactive Machines 1.3.4 Limited Memory 1.3.5 Theory of Mind 1.3.6 Self-Awareness 1.4 Is Artificial Intelligence Same as Augmented Intelligence and Cognitive Computing? 1.5 Machine Learning and Deep Learning 1.6 Applications of AI 1.7 Robotics—an Application of AI 1.7.1 Types of Robots 1.7.2 Uses of Robotics 1.8 Drones Using AI 1.9 The Future of AI 1.10 No Code AI 1.10.1 Why No-Code AI? 1.10.2 Future of No Code AI 1.10.3 Why No-Code AI Must be Used? 1.11 Low Code AI 1.11.1 Low-Code vs No-Code AI Development 1.11.2 Who Uses Low-Code Development? 1.11.3 Low-Code AI Platform for Computer Vision 1.11.4 Components of Low-Code AI Platforms 1.11.5 Disadvantages of Low-Code/No-Code Platforms 1.11.6 Is Low-Code the Future of Software Development? Programmer’s Zone Key Terms Recapitulation Points Answer the Questions Fill Up State True or False Multiple Choice Questions Find Out Three AI Tools for Application Based Questions Links to Explore Answers 2. Artificial Intelligence Technologies 2.1 Techniques in AI 2.2 Machine Learning Model 2.2.1 Types of Machine Learning Algorithms 2.3 Regression Analysis in Machine Learning 2.3.1 How Regression Analysis Works? 2.3.2 Model Evaluation Metrics 2.3.3 Types of Regression 2.4 Classification Techniques 2.4.1 K-Nearest Algorithm 2.4.2 Decision Trees 2.4.3 Random Forests 2.5 Clustering Techniques 2.5.1 Overview of Clustering Techniques 2.5.2 K-Means Algorithm 2.5.3 Applications of Clustering in Real-World Scenarios 2.5.4 Evaluation Metrics for Clustering 2.5.5 How K-Means Algorithm Works? 2.5.6 Pros and Cons of K-Means Algorithm 2.5.7 Density-Based Spatial Clustering of Applications with Noise (Dbscan) 2.6 Naïve Bayes Classification 2.6.1 Understanding Conditional Probability 2.6.2 The Bayes Rule 2.6.3 Types of Events 2.6.4 Naive Bayes Algorithm 2.6.5 Laplace Correction 2.6.6 Pros and Cons of Naive Bayes Algorithm 2.6.7 Applications 2.7 Neural Network 2.7.1 Working of Neural Networks 2.7.2 Pros and Cons 2.7.3 Applications of Neural Networks 2.7.4 How Neural Networks Work? 2.7.5 What is an Activation Function? 2.7.6 Gradient Descent 2.8 Support Vector Machine (SVM) 2.8.1 How Does SVM Work? 2.8.2 Advantages of SVM 2.8.3 Disadvantages of SVM 2.8.4 Applications of SVM in Real World Key Terms Recapitulation Points Answer the Questions Fill Up State True or False Multiple Choice Questions Case Study-Based Assignment Enhancing Audio, Visual and Cognitive Skills Answers 3. Artificially Intelligent Machine 3.1 Defining Intelligence 3.2 Components of Intelligence 3.3 Differences Between Human and Machine Intelligence 3.4 Agent and Environment 3.4.1 Key Terminology 3.4.2 Rationality 3.4.3 Structure of Intelligent Agents 3.4.4 Types of Agents 3.4.5 The Nature of Environments 3.4.6 Types of Environments 3.5 Search 3.5.1 Types of Search Algorithms 3.5.2 Properties of Search Algorithms 3.6 Uninformed Search Algorithms 3.6.1 Depth First Search (DFS) 3.6.2 Depth-Limited Search Algorithm (DLS) 3.6.3 Breadth First Search (BFS) 3.6.4 Uniform Cost Search (UCS) 3.6.5 Iterative Deepening Depth-First Search (IDDFS) 3.6.6 Bidirectional Search 3.7 Informed Search Algorithms 3.7.1 Pure Heuristic Search 3.7.2 Best-First Search Algorithm (Greedy Search) 3.7.3 A* Search Algorithm 3.7.4 AO* Algorithm 3.8 Hill Climbing Algorithm in Artificial Intelligence 3.8.1 Features of Hill Climbing 3.8.2 Types of Hill Climbing 3.8.3 State Space Diagram for Hill Climbing 3.8.4 Simulated Annealing 3.8.5 Applications 3.8.6 Pros and Cons of Hill Climbing Algorithms 3.9 Adversarial Search 3.9.1 Game Scenarios 3.9.2 Key Terminology 3.9.3 Game Tree 3.9.4 Uses of Adversarial Search 3.9.5 Mini-Max Algorithm 3.10 Alpha-Beta Pruning 3.10.1 Pseudo-Code for Alpha-Beta Pruning 3.10.2 Worst-Case and Best-Case in Alpha-Beta Pruning 3.11 Local Search Algorithms 3.11.1 Hill-Climbing Search 3.11.2 Local Beam Search 3.11.3 Simulated Annealing 3.11.4 Travelling Salesman Problem 3.12 Single Agent Path-Finding Problems 3.12.1 Search Terminology 3.12.2 Brute-Force Search Strategies Programmer’s Zone Key Terms Recapitulation Points Answer the Questions Fill Up State True or False Multiple Choice Questions Answers 4. Knowledge Representation 4.1 Introduction 4.2 Knowledge Representation 4.2.1 What Knowledge Needs to be Represented? 4.2.2 What is Knowledge? 4.2.3 What is Logic? 4.2.4 Cycle of Knowledge Representation in AI 4.2.5 Knowledge Representation Requirements 4.3 Knowledge-Based Agent 4.3.1 The Architecture of Knowledge-Based Agent 4.3.2 Operations Performed By KBA 4.3.3 A Generic Knowledge-Based Agent 4.3.4 Various Levels of Knowledge-Based Agent 4.3.5 Approaches to Designing a Knowledge-Based Agent 4.4 Types of Knowledge 4.5 Techniques of Knowledge Representation in AI 4.5.1 Logical Representation 4.5.2 Semantic Network Representation 4.5.3 Frame Representation 4.5.4 Production Rules 4.5.5 Propositional Logic (PL) 4.6 Syntax of Propositional Logic 4.7 Logical Connectives in Propositional Logic 4.7.1 Logical Equivalence 4.7.2 Truth Table of Propositional Connectives 4.7.3 Precedence of Connectives 4.7.4 Properties of Operators 4.7.5 Limitations of Propositional Logic 4.8 Inference Rules 4.8.1 Types of Inference Rules 4.8.2 First-Order Logic 4.8.3 Generalized Modus Ponens Rule 4.8.4 Unification in FOL 4.8.5 Unification Algorithm 4.8.6 Resolution 4.8.7 The Resolution Inference Rule 4.8.8 The Resolution Process 4.8.9 Explanation of Resolution Graph 4.9 Forward Chaining and Backward Chaining in AI 4.9.1 Horn Clause and Definite Clause 4.9.2 Forward Chaining 4.9.3 Forward Chaining Algorithm 4.9.4 Why Do We Use Forward Chaining? 4.9.5 Backward Chaining 4.9.6 Pros and Cons of Backward Chaining Programmer’s Zone Key Terms Recapitulation Points Answer the Questions Fill Up State True or False Multiple Choice Questions Answers 5. Reasoning and Learning in Artificial Intelligence 5.1 Reasoning 5.1.1 Features of a Reasoning System 5.1.2 Why Focus on Reasoning System? 5.1.3 Methods of Reasoning 5.2 Probabilistic Reasoning in Artificial Intelligence 5.2.1 Uncertainty 5.2.2 Probability 5.3 Bayes’ Theorem 5.3.1 Bayesian Belief Network in Artificial Intelligence 5.3.2 Joint Probability Distribution 5.3.3 Understanding the Semantics of Bayesian Network 5.4 Learning 5.4.1 Components of a Learning System 5.4.2 Forms of Learnings 5.5 Clustering 5.5.1 Clusters 5.5.2 Overview of Clustering Techniques 5.6 Explanation-Based Learning (EBL) 5.7 Reinforcement Learning 5.7.1 Components of Reinforcement Learning 5.7.2 Example: Reinforcement Learning in Real World 5.7.3 Characteristics of Reinforcement Learning 5.7.4 Differences Between Reinforcement Learning and Supervised Learning 5.7.5 Types of Reinforcement 5.7.6 Applications of Reinforcement Learning 5.7.7 When to Use Reinforcement Learning in a Large Environment? 5.7.8 Benefits of Reinforcement Learning 5.7.9 Challenges with Reinforcement Learning 5.7.10 Future of Reinforcement Learning 5.7.11 When Not to Use Reinforcement Learning? Programmer’s Zone Key Terms Recapitulation Points Answer Them Fill Up State True or False Multiple Choice Questions Answers 6. Computer Vision (CV) 6.1 Human Vision vs Computer Vision 6.2 How Does Computer Vision Work? 6.3 The Evolution of Computer Vision 6.4 Tasks in Computer Vision 6.5 How Computer Vision Works with Deep Learning? 6.6 Applications of Computer Vision 6.7 Which Vision Succeeded? 6.8 Challenges in Computer Vision 6.9 Understanding Image Pixels 6.9.1 What is Resolution? 6.9.2 DPI and PPI 6.10 Convolutional Neural Networks (CNN) 6.10.1 Understanding the Working of a Simple CNN 6.10.2 THE Pooling Layer 6.10.3 Limitations 6.11 Working with Images Using OpenCV 6.12 Immersive Experience 6.12.1 Elements of Immersion 6.12.2 Types of Immersive Experiences 6.12.3 Applications of Immersive Experiences 6.12.4 Virtual Reality Systems 6.12.5 Types of Augmented Reality 6.12.6 Mixed Reality 6.12.7 Challenges of Immersive Experiences Programmer’s Zone Key Terms Recapitulation Points Review Questions Fill Up State True or False Multiple Choice Questions Identify the Process Answers 7. Natural Language Processing 7.1 What is Natural Language Processing? 7.2 Everyday NLP Examples 7.3 Chatbot 7.3.1 Open and Closed Chatbots 7.3.2 Uses of Chatbots 7.3.3 How a Chatbot Works? 7.3.4 Types of Chatbots 7.4 How Does Natural Language Processing Work? 7.5 Components of NLP 7.6 Steps in NLP NLP, AI, Machine Learning: What’s the Difference? 7.7 Phases of NLP Data Pre-Processing Data Processing 7.8 Syntax vs Semantic Analysis 7.9 Applications of Natural Language Processing 7.10 Pros and Cons of Natural Language Processing Limitations of NLP Systems Challenges 7.11 Evolution of Natural Language Processing 7.12 Handling Ambiguities 7.12.1 Techniques of Ambiguity Resolution 7.13 The NLP Model of Perception 7.13.1 NLP Communication Model 7.13.2 The Five Perceptual Positions 7.14 Constituency Grammar 7.15 Context-Free Grammar 7.15.1 Derivations 7.15.2 Using Nominals in CFG 7.15.3 Uses of CFG 7.15.4 Types of Derivation 7.15.5 Parse Tree 7.15.6 Ambiguity in CFG 7.15.7 Parser 7.16 Speech Recognition 7.16.1 How Does Speech Recognition Work? 7.16.2 Applications of Speech Recognition 7.16.3 Algorithms for Speech Recognition 7.16.4 Advantages of Speech Recognition 7.16.5 Disadvantages of Speech Recognition Programmer’s Zone Key Terms Recapitulation Points Review Questions Fill Up State True or False Multiple Choice Questions Answers 8. Current Trends in Artificial Intelligence 8.1 AI and Ethical Concerns 8.1.1 Ethical Use of Artificial Intelligence 8.1.2 Is AI Dangerous? Will Robots Take Over the World? 8.1.3 Ethics in AI 8.1.4 AI and Bias 8.1.5 Towards Ethical and Trustworthy AI 8.1.6 Why is Ethical AI Important? 8.1.7 Impact of AI on Jobs 8.2 AI as a Service (AIaaS) 8.2.1 Factors Triggering Growth of AIaaS 8.2.2 The Growth of AIaaS 8.2.3 Challenges of AIaaS 8.2.4 Vendors of AIaaS 8.3 Robotics 8.3.1 Artificially Intelligent Robot 8.3.2 Characteristics of Robots 8.3.3 Types of Robots 8.3.4 Types of Robots Based on Degree of Human Control 8.3.5 Components of a Robot 8.3.6 AI Technology Used in Robotics 8.3.7 Planning and Navigation 8.4 Recent Trends in AI 8.4.1 Collaborative Systems 8.4.2 Machines Assisting Humans 8.4.3 Algorithmic Game Theory and Computational Social Choice 8.4.4 Multi-Agents Reinforcement Learning (MARL) 8.4.5 Neuromorphic Computing Programmer’s Zone Key Terms Recapitulation Points Review Questions Fill Up State True or False Multiple Choice Questions Answers 9. Where AI Is Heading Today? 9.1 Expert System 9.1.1 Popular Examples of the Expert System 9.1.2 Characteristics of an Expert System 9.1.3 Components of an Expert System 9.1.4 Participants in the Development of Expert System 9.1.5 Capabilities of the Expert System 9.1.6 Advantages of Expert Systems 9.1.7 Limitations of Expert Systems 9.1.8 Applications of Expert Systems 9.1.9 Expert System Technology 9.1.10 Development of Expert Systems 9.2 Internet of Things 9.2.1 Examples of Applications of IoT 9.2.2 IoT Products 9.2.3 Challenges 9.2.4 Sensors 9.3 Artificial Intelligence of Things (AIoT) 9.3.1 How Does AIoT Work? 9.3.2 Where Does AI Unlock IoT? 9.3.3 Applications and Examples of AIoT 9.3.4 Benefits and Challenges of AIoT 9.3.5 Future of AIoT 9.4 Edge Computing 9.4.1 Why is Edge Computing Important? 9.4.2 Edge Computing Use Cases and Examples 9.4.3 Benefits of Edge Computing 9.4.4 Challenges of Edge Computing 9.4.5 Edge Computing Implementation 9.4.6 Edge Computing, IoT and 5G Possibilities 9.5 Metaverse 9.5.1 Use Cases of Metaverse 9.5.2 Where is Metaverse Today? Key Terms Recapitulation Points Review Questions Fill Up State True or False Multiple Choice Questions Answers 10. AI Evolving with New Age Techniques 10.1 Fuzzy Logic 10.1.1 Characteristics of Fuzzy Logic 10.1.2 Architecture of a Fuzzy Logic System 10.1.3 Membership Function 10.1.4 Example of a Fuzzy Logic System 10.1.5 Classical and Fuzzy Set Theory 10.1.6 Fuzzy Set 10.1.7 Applications of Fuzzy Logic 10.1.8 Advantages of Fuzzy Logic 10.1.9 Disadvantages of Fuzzy Logic 10.1.10 Trends 10.2 Genetic Algorithms 10.2.1 Advantages of Genetic Algorithms 10.2.2 Limitations of Genetic Algorithms 10.2.3 Basic Terminology 10.2.4 Basic Structure 10.2.5 Genotype Representation 10.2.6 Population 10.2.7 Population Initialization 10.2.8 Population Models 10.2.9 Fitness Function 10.2.10 Parent Selection 10.2.11 Crossover 10.2.12 Mutation 10.2.13 Termination Condition 10.2.14 Application Areas 10.3 Soft Computing 10.3.1 Characteristics of Soft Computing 10.3.2 Need for Soft Computing 10.3.3 Applications of Soft Computing 10.3.4 Elements of Soft Computing 10.4 Transfer Learning 10.4.1 How Transfer Learning Works? 10.4.2 When to Use Transfer Learning 10.4.3 Approaches to Transfer Learning 10.4.4 Traditional Machine Learning vs Transfer Learning 10.4.5 Classical Transfer Learning Strategies 10.4.6 Transfer Learning for Deep Learning 10.4.7 Steps in Transfer Learning 10.4.8 Types of Deep Transfer Learning 10.4.9 Applications of Transfer Learning 10.4.10 When Does Transfer Learning Not Work? Key Terms Recapitulation Points Review Questions Fill Up State True or False Multiple Choice Questions Answers Programming Language Prolog Case Study Case Study 1: N Queen Problem with Backtracking Case Study 2: Warnsdorff’s Algorithm For Knight’s Tour Problem Case Study 3: Rat in a Maze Case Study 4: Unique Paths in A Grid Case Study 5: The Wumpus World Case Study 6: Smart Cities Index Copyright