The book is a comprehensive source which explores the fundamental principles, evolution, and applications of intelligent systems in a structured manner. It provides readers with a deep understanding of how machines can learn, reason, and make autonomous decisions, bridge the gap between theory and practical implementations. It emphasises conceptual clarity, real-world relevance, and ethical perspectives, and is suitable for students, educators, and professionals. It deals with diverse fields such as healthcare, education, finance, and robotics. This book equips readers with the knowledge and analytical skills needed to innovate and contribute effectively to the changing world of Intelligent Technologies.
Contents –
1. Introduction to Artificial Intelligence
1.1 Intelligence
1.1.1 Definitions of Intelligence
1.1.2 Characteristics of Intelligence
1.1.3 Real-Time Examples of Intelligence
1.2 Definitions and Goals of AI
1.2.1 Definitions of Artificial Intelligence
1.2.2 Goals of Artificial Intelligence (AI)
1.2.3 History of Artificial Intelligence
1.2.4 AI vs Human Intelligence
1.2.5 Narrow AI, General AI and Super AI
1.2.5.1 Narrow AI (Artificial Narrow Intelligence) Narrow AI (Weak AI)
1.2.5.2 Artificial General Intelligence (AGI): General AI (Strong AI)
1.2.5.3 Super AI (Artificial Superintelligence)
1.2.5.4 Comparison Between Narrow AI, General AI and Super AI
1.3 AI Techniques
1.3.1 Search in Artificial Intelligence (AI)
1.3.2 Knowledge Representation in Artificial Intelligence (AI)
1.3.3 Learning in Artificial Intelligence (AI)
1.4 AI Techniques and Problem Solving
1.4.1 State Space Search
1.4.1.1 Principles of State Space Search
1.4.1.2 Steps in State Space Search
1.4.1.3 State Space Search: Breadth-First Search (BFS) Algorithm on the 8-Puzzle Problem
1.4.1.4 Applications of State Space Search
1.4.1.5 Challenges in State Space Search
1.4.2 Production System in Artificial Intelligence
1.4.2.1 Components of a Production System
1.4.2.2 Working of a Production System
1.4.2.3 Types of Production Systems
1.4.2.4 Applications of Production Systems
1.4.2.5 Advantages of Production Systems
1.4.2.6 Challenges in Production Systems
1.4.3 Heuristic Search Techniques
1.4.3.1 Components of Heuristic Search
1.4.3.2 Types of Heuristic Search Techniques
1.4.3.2.1 Generate-And-Test Algorithm
1.4.3.2.2 Hill Climbing
1.4.3.2.3 Best First Search (Informed Search)
1.4.3.2.4 A* Search Algorithm
1.5 Applications of Artificial Intelligence (AI) in Various Domains
1.5.1 Healthcare
1.5.2 Finance
1.5.3 Retail and E-Commerce
1.5.4 Manufacturing
1.5.5 Transportation
1.5.6 Education
1.6 Ethical Challenges in AI
1.6.1 Bias and Fairness
1.6.2 Transparency and Explainability
1.6.3 Privacy and Data Security
1.6.4 Job Displacement and Economic Impact
1.6.5 Accountability and Liability
1.6.6 Ethical Use of Autonomous Weapons
1.6.7 Manipulation and Misinformation
1.6.8 Ethical AI Governance and Regulations
1.7 Problem Representation and Search
1.7.1 Components of State Space Representation
1.7.2 Characteristics of Search Problems
1.7.2.1 Observability
1.7.2.2 Determinism
1.7.2.3 Static Nature
1.8 Production Systems and Problem Design
1.9 AI vs Human Intelligence
1.9.1 Comparison Between AI and Human Cognitive Functions
1.10 Memory vs Computational Trade-offs in AI.
2. Knowledge Representation and Reasoning
2.1 Represent with in AI Systems
2.1.1 Types of Knowledge in AI
2.1.1.1 Descriptive Knowledge
2.1.1.2 Imperative Knowledge
2.1.1.3 Meta-Knowledge
2.1.1.4 Heuristic Knowledge
2.1.1.5 Relational Knowledge
2.1.2 Mapping the Path Between Knowledge and Intelligence
2.1.3 AI Knowledge Cycle
2.1.4 Approaches to Knowledge Representation
2.1.5 Requirements for Knowledge Representation System
2.2 Importance of AI
2.3 Logical Representation
2.3.1 Propositional vs Predicate Logic
2.3.2 Difference Between Propositional Logic and Predicate Logic
2.3.3 Instance and ISA Relationship
2.4 Symbolic Reasoning and Uncertainty
2.4.1 Procedural Vs. Declarative Knowledge in Artificial Intelligence
2.4.1.1 Procedural Knowledge in AI
2.4.1.2 Advantages of Procedural Knowledge
2.4.1.3 Declarative Knowledge in AI
2.4.1.4 Advantages of Declarative Knowledge
2.4.1.5 Difference Between Procedural vs Declarative Knowledge in Artificial Intelligence
2.4.2 Symbolic Reasoning Under Uncertainty
2.4.2.1 Reasoning
2.4.2.2 Approaches to Reasoning
2.4.2.3 Uncertainty in Reasoning
2.4.2.4 Monotonic Reasoning
2.4.3 Non-monotonic Reasoning
2.4.3.1 Logics for Non-monotonic Reasoning
2.5 Logic Programming
2.5.1 Introduction to Prolog
2.5.1.1 Prolog – Basics
2.5.1.2 Working Model of Prolog
2.5.1.3 Applications of Prolog
2.5.1.4 Strengths of Prolog
2.5.1.5 Limitations
2.5.1.6 Prolog – Relations
2.5.1.7 Prolog – Data Objects
2.5.1.8 Prolog – Operators
2.5.1.9 Prolog – Loop
2.5.1.10 Decision Making
2.5.2 Forward and Backward Reasoning
2.5.2.1 Forward Reasoning
2.5.2.2 Backward Reasoning
2.5.2.3 Forward vs Backward Reasoning – Comparison Table
2.5.3 Deductive Reasoning (Resolution and Natural Deduction)
2.5.3.1 Applications of Deductive Reasoning in AI
2.5.3.2 Challenges and Limitations
2.6 Knowledge Representation Structures
2.6.1 Semantic Networks
2.6.1.1 Types of Semantic Networks
2.6.1.2 Components of Semantic Networks in AI
2.6.1.3 Working Model of Semantic Networks
2.6.1.4 Applications of Semantic Networks in AI
2.6.1.5 Advantages of Semantic Networks in AI
2.6.2 Frames in AI: Knowledge Representation and Inheritance
2.6.2.1 Frames in AI
2.6.2.2 Introduction to Frame Inheritance
2.6.2.3 Benefits of Frame Inheritance
2.6.2.4 Applications of Frames in AI
2.6.2.5 Advantages of Frames in AI
2.6.3 Conceptual Dependency in AI
2.6.3.1 Conceptual Dependency (CD) Theory
2.6.3.2 Concepts in Conceptual Dependency
2.6.3.3 Components of Conceptual Dependency
2.6.3.4 Importance of Conceptual Dependency Theory
2.6.3.5 Working of Conceptual Dependency
2.6.3.6 Conceptual Dependency benefits
2.6.4 Scripts in AI
2.6.4.1 Script Theory
2.6.4.2 Components of Script Theory
2.6.4.3 Applications of Script Theory in AI
2.6.4.4 Advantages of Using Script Theory in AI
2.6.4.5 Future Directions
2.6.5 CYC (Large-Scale Knowledge Representation)
2.6.5.1 CYC
2.6.5.2 Features of CYC
2.6.5.3 Applications of CYC
2.6.5.4 Significance of CYC
2.6.5.5 Challenges with CYC
2.7 Search Problem Components in AI
2.7.1 Types of Search Algorithms
2.7.1.1 Depth-First Search (DFS)
2.7.1.2 Characteristics of Depth-First Search (DFS)
2.7.1.3 Breadth-First Search
2.7.1.4 Characteristics of BFS
2.7.1.5 Applications of BFS
2.7.2 Problem Solving in Artificial Intelligence
2.7.2.1 Concepts in AI Problem Solving
2.7.2.2 Types of Problems in AI
2.7.2.3 Challenges in AI Problem Solving
2.8 Advanced Logic and Reasoning Techniques in AI
2.8.1 Slot-Filler Structures in AI
2.8.1.1 Slot-Filler Structures
2.8.1.2 Characteristics of Slot-Filler Structures
2.8.1.3 Advanced Uses of Slot-Filler Structures
2.8.1.4 Advantages of Slot-Filler Structures
2.8.1.5 Comparison of Various AI Representation Techniques
3 Statistical and Probabilistic Reasoning
3.1 Introduction to Probability and Bayesian Networks
3.1.1 Probability
3.1.2 Key Terminologies
3.1.3 Probability Axioms
3.1.4 Probability Formula
3.1.5 Joint and Conditional Probability
3.1.5.1 Joint Probability
3.1.5.2 Conditional Probability
3.1.5.3 Relationship Between Joint and Conditional Probability
3.1.5.4 Law of Total Probability
3.1.5.5 Bayes’ Theorem
3.1.5.6 Applications in AI and ML
3.1.6 Bayes’ Theorem
3.1.6.1 Understanding the Components
3.1.6.2 Applications in AI and ML
3.2 Bayesian Networks and Certainty Factors
3.2.1 Structure of Bayesian Networks
3.2.2 Inference Using Bayesian Networks
3.3.2.1 Types of Inference in Bayesian Networks
3.3.2.2 Steps in Bayesian Network Inference
3.2.2.3 Key Algorithms for Inference
3.2.2.4 Handling Larger Bayesian Networks
3.2.2.5 Applications of Inference in Bayesian Networks
3.2.3 Certainty Factors in Expert Systems
3.2.3.1 Definition of Certainty Factors
3.2.3.2 Key Characteristics of Certainty Factors
3.2.3.3 Combining Certainty Factors
3.2.3.4 Certainty Factors in MYCIN
3.2.3.5 Advantages and Limitations of Certainty Factors
3.2.3.6 Applications of Certainty Factors
3.2.3.7 Comparison between Bayesian Networks and Certainty Factors
3.3 Dempster-Shafer Theory
3.3.1 Introduction
3.3.1.1 Key Concepts of Dempster – Shafer Theory
3.3.1.2 Steps in Applying Dempster – Shafer Theory
3.3.1.3 Advantages and Disadvantages
3.3.2 Uncertainty Handling in Dempster – Shafer Theory
3.3.3 Belief Networks in Dempster – Shafer Theory
3.3.3.1 Structure of Belief Networks
3.3.3.2 Key Features of Belief Networks in DST
3.3.3.3 Applications of DST and Belief Networks
3.3.3.4 Advantages, Challenges and Limitations
3.3.4 Comparison of Bayesian Networks and Belief Networks
3.4 Knowledge Structures and Frames
3.4.1 Introduction to Knowledge Representation
3.4.2 Strong and Weak Slot-Filler Structures in AI
3.4.2.1 Strong Slot-Filler Structures
3.4.2.2 Weak Slot-Filler Structures
3.4.3 Semantic Networks in Artificial Intelligence
3.4.3.1 Structure of a Semantic Network
3.4.3.2 Types of Semantic Networks
3.4.3.3 Example of a Semantic Network
3.4.3.4 Advantages and Disadvantages of Semantic Networks
3.4.3.5 Applications and Advanced Concepts in Semantic Networks
3.4.4 Frames in Artificial Intelligence
3.4.4.1 Structure of a Frame
3.4.4.2 Key Features of Frames
3.4.4.3 Representation of Frames
3.4.4.4 Algorithms in Frame-Based Systems
3.4.4.5 Applications of Frames
3.4.4.6 Advantages and Limitations of Frames
3.4.5 Scripts in Artificial Intelligence
3.4.5.1 Structure of a Script
3.4.5.2 Representation of Scripts
3.4.5.3 Characteristics of Scripts
3.4.5.4 Advantages and Limitations of Scripts
3.4.5.5 Applications of Scripts
3.5 Probabilistic Representation Techniques
3.5.1 Introduction
3.5.1.1 Types of Probabilistic Representation Techniques
3.5.1.2 Applications of Probabilistic Representation
3.5.1.3 Advantages and Limitations of Probabilistic Techniques
3.5.2 Semantic Spectrum
3.5.2.1 Levels of the Semantic Spectrum
3.5.2.2 Applications of the Semantic Spectrum
3.5.3 Logic Structures in AI
3.5.3.1 Types of Logic Structures
3.5.3.2 Representation of Logic Structures
3.5.3.3 Applications of Logic Structures in AI
3.5.3.4 Advantages and Limitations of Logic Structures
3.5.4 Applications of AI
3.6 Advanced Probabilistic Models
3.6.1 Introduction
3.6.1.1 Advanced Probabilistic Models
3.6.1.2 Mathematical Foundations
3.6.1.3 Applications of Advanced Probabilistic Models
3.6.1.4 Advantages and Challenges of Advanced Probabilistic Models
3.6.2 Use of Semantic Nets and Frames for Advanced Problem Solving
3.6.2.1 Semantic Nets in Advanced Problem Solving
3.6.2.2 Frames in Advanced Problem Solving
3.6.2.3 Combining Semantic Nets and Frames
3.6.2.4 Challenges and Considerations
4. Machine Learning Fundamentals
4.1 Introduction to Machine Learning
4.1.1 The Evolution of Machine Learning
4.1.2 Types of Machine Learning
4.1.3 Key Components of Machine Learning
4.1.4 Applications of Machine Learning
4.1.5 Difference Between AI, Machine Learning, and Big Data
4.1.6 Applications in AI, Data Science, and Big Data
4.2 Supervised Learning Models
4.2.1 Parametric Models
4.2.2 Naive Bayes Classifier
4.2.2.1 Types of Naive Bayes Classifiers
4.2.2.2 Advantages and Limitations of Naive Bayes Classifier
4.2.3 Non-Parametric Classifiers (KNN)
4.2.3.1 K-Nearest Neighbours (KNN)
4.2.3.2 Working of KNN – Step-by-Step
4.2.3.3 Common Distance Metrics
4.2.3.4 Advantages and Disadvantages
4.3 Unsupervised Learning Models
4.3.1 Applications of Unsupervised Learning Models
4.3.2 Clustering Techniques
4.3.2.1 K-Means Clustering
4.3.2.2 Hierarchical Clustering
4.3.2.2.1 Agglomerative Clustering
4.3.2.2.2 Divisive Hierarchical Clustering
4.3.3 Dimensionality Reduction
4.3.3.1 Principal Component Analysis (PCA)
4.3.3.2 Linear Discriminant Analysis (LDA)
4.4 Support Vector Machines and Kernel Methods
4.4.1 Key Concepts of SVM
4.4.2 Kernel Functions
4.4.2.1 Types of Kernel Functions
4.4.3 Model Selection and Tuning
4.4.3.1 Model Tuning (Hyperparameter Optimization)
4.5 Model Evaluation and Regularization
4.5.1 Overfitting in Model Evaluation
4.5.1.1 Model Evaluation Techniques to Mitigate Overfitting
4.5.2 Underfitting in Model Evaluation
4.5.3 Cross-Validation Techniques
4.5.3.1 Cross-Validation Techniques
4.5.4 Regularisation Methods
4.5.4.1 Types of Regularisation Methods
4.6 Bias-Variance Trade-off
4.6.1 Managing Model Complexity and Performance
4.6.1.1 Strategies to Manage Model Complexity
5. Neural Networks, Genetic Algorithms and Advanced Learning
5.1 Introduction to Neural Learning
5.1.1 Basic Structure of Neural Networks
5.1.2 Types of Neural Networks
5.1.3 How Neural Networks Learn (Training Process)
5.1.4 Applications of Neural Networks
5.2. Perceptron Model
5.2.1 Basic Components of Perceptron
5.2.2 Types of Perceptron
5.2.3 Working Model of Perceptron
5.2.4 Characteristics of the Perceptron Model
5.2.5 Perceptron Learning Rule
5.2.6 Perceptron Function
5.2.7 Input of a Perceptron
5.2.8 Output of Perceptron
5.3 Multilayer Perceptron (Backpropagation)
5.3.1 Workings of a Multilayer Perceptron
5.3.2 Stochastic Gradient Descent (SGD)
5.3.3 Backpropagation
5.4 Applications in Pattern Recognition
5.4.1 Introduction
5.4.2 Training and Learning in Pattern Recognition
5.4.3 Applications
5.5 Advanced Neural Networks
5.5.1 Convolutional Neural Networks (CNNs)
5.5.1.1 CNN and Parallels with Human Visual System
5.5.1.2 Components of a CNN
5.5.1.3 Different Types of CNN Models
5.5.1.4 Application of CNN
5.5.2 Recurrent Neural Networks (RNNs)
5.5.3 Deep Learning Architectures
5.5.3.1 Scope of Deep Learning
5.5.3.2 Difference Between Machine Learning and Deep Learning
5.5.3.3 Types of Neural Networks
5.5.3.4 Deep Learning Applications
5.6 Genetic Algorithms and Evolutionary Strategies
5.6.1 Concepts of Genetic Algorithms
5.6.1.1 Foundation of Genetic Algorithms
5.6.1.2 Basic Structure
5.6.2 Mutation
5.6.2.1 Role and Importance of Mutation
5.6.2.2 Working Model of Mutation
5.6.2.3 Types of Mutation Operators
5.6.3 Crossover
5.6.3.1 Different Types of Crossover
5.6.4 Evolutionary Strategies for Optimisation
5.6.4.1 Principles of Evolutionary Strategies
5.6.4.2 Algorithm Workflow
5.6.4.3 Applications of Evolutionary Strategies
5.7 Bayesian Learning and EM Algorithm
5.7.1 Maximum Likelihood Estimation (MLE)
5.7.2 Bayesian Networks
5.7.3 Expectation-Maximisation (EM) Algorithm
5.7.3.1 Working Model of Expectation-Maximisation (EM) Algorithm
5.7.3.2 Expectation-Maximisation Algorithm Step by Step Implementation
5.8 Reinforcement Learning
5.8.1 Terms Used in Reinforcement Learning
5.8.2 Types of Reinforcement
5.8.3 Reinforcement Learning Applications
5.8.4 Q-Learning
5.8.5 Temporal Difference Learning
5.8.5.1 Temporal Difference Learning Algorithms
5.8.6 Policy Learning
5.9 Deep Reinforcement Learning
5.9.1 Applications in Game AI
5.9.2 Robotics and Autonomous Systems
6. Advanced Topics in AI and Applications
6.1 Natural Language Processing (NLP)
6.1.1 NLP Challenges
6.1.1.1 Challenges in NLP
6.1.2 Syntactic and Semantic Analysis
6.1.3 Pragmatic Processing
6.2 Game Playing and Planning Systems
6.2.1 Minimax Algorithm
6.2.2 Alpha-Beta Pruning
6.2.3 Planning Systems (Goal Stack, Hierarchical Planning)
6.2.3.1 Goal Stack Planning
6.2.3.2 Hierarchical Planning in AI
6.3 Recommendation Systems and Opinion Mining
6.3.1 Collaborative Filtering
6.3.1.1 User-based Collaborative Filtering
6.3.1.2 Item-Based Collaborative Filtering
6.3.2 Content-Based Filtering
6.3.3 Opinion Mining
6.3.4 Sentiment Analysis
6.4 Expert Systems and Knowledge Acquisition
6.4.1 Introduction to Expert Systems
6.4.2 Expert System Shells
6.4.3 Knowledge Acquisition
6.4.4 Applications in Medical Diagnosis
6.5 Fuzzy Logic and Neuro-Fuzzy Systems
6.5.1 Fuzzy Logic Basics
6.5.1.1 Architecture
6.5.1.2 Applications of Fuzzy Logic in AI
6.5.2 Crisp Sets, Fuzzy Sets
6.5.2.1 Crisp Sets
6.5.2.2 Fuzzy Sets
6.5.2.3 Between Crisp Set and Fuzzy Set
6.5.3 Fuzzy Rules, Neuro-Fuzzy Systems
6.5.3.1 FUZZY RULES
6.5.3.2 NEURO-FUZZY SYSTEMS
6.6 AI Applications in Various Domains
6.6.1 Applications in Healthcare
6.6.2 AI Applications in Education
6.6.3 Applications in Autonomous Systems
6.6.4 Ethics and Social Implications
