Artificial intelligence (AI) has evolved from a theoretical pursuit within computer science into one of the most transformative forces shaping modern society. This book aims to guide readers through the core principles, methodologies, architectures, and applications of AI, beginning with classical symbolic AI and progressing towards modern data-driven and learning-based approaches. Rather than treating AI as a collection of isolated techniques, this text presents it as an integrated discipline built on knowledge representation, reasoning, search, planning, learning, and intelligent decision-making. Salient features
Chandramouli Subramanian is Associate Director at Cognizant Technology Solutions, Chennai, Tamil Nadu. An alumnus of IIM-K and a Certified Global Business Leader from Harvard Business School, he is a prolific writer of business management articles dealing with design thinking, technology management, delivery management, competitiveness, IT, organizational culture, and leadership.
Asha A George is an accomplished technologist and author with over 25 years of experience in the IT industry. Her expertise spans systems development, integration, and advanced consulting. She is certified in Blockchain, Project Portfolio Management (PPM), Six Sigma, COBIT, ITIL, Scrum, and other key project management and governance frameworks.
About the Authors Preface Acknowledgements
Chapter 1: Introduction to Artificial Intelligence Introduction | The Architecture of AI Systems | The AI Development Life Cycle | Key Terms and Concepts in AI | Knowledge Representation Methods | Domains and Scope of AI Applications | AI System Interface – Sensing, Control, and Actuation | Intelligent Agents and their Characteristics | Expert Knowledge-based Systems | Categorisation of Intelligent Systems | AI Tools and their Applications | Summary | Exercises
Chapter 2: State-Space Representation Introduction | Characteristics of State-space Representation | Knowledge Representation Techniques | Conceptual Modelling in State Space | Summary | Exercises
Chapter 3: Problem Solving Introduction | Solving Problems by Search | Uninformed (Blind) Search Strategies | Informed (Heuristic) Search Strategies | Constraint Satisfaction Problems | Constraint Satisfaction Problem Techniques | Summary | Exercises
Chapter 4: Game Playing Introduction | Game Theory | Adversarial Search | Imperfect Real-time Decisions | Stochastic Games | Applications of Stochastic Games in AI | Summary | Exercises
Chapter 5: Intelligent Agents Introduction | Intelligent Agents | Multi-Agent Systems | Agent Communication | Agent Coordination | Intelligent Mobile Agents | Summary | Exercises
Chapter 6: Knowledge and Reasoning Introduction | Cycle of Knowledge Representation and Reasoning | Knowledge Representation and Reasoning System | The Wumpus World Problem | Probabilistic Reasoning | Bayesian Probability | Markov Models | Implementing KRR in Intelligent Systems | Benefits and Applications of KRR in AI | Summary | Exercises
Chapter 7: Expert Systems Introduction | Characteristics of Expert Systems | Architecture of an Expert System | Types of Expert Systems | Expert System Development Life Cycle | Advantages and Limitations of Expert Systems | Real-World Applications of Expert Systems | Summary | Exercises
Chapter 8: Fundamentals of Machine Learning Introduction | Types of Machine Learning | Machine Learning Algorithms | Other Branches of Machine Learning | Summary | Exercises
Chapter 9: Reinforcement Learning Introduction | Reinforcement Learning Approaches | RL Foundational Concepts and Frameworks | Reinforcement Learning Methods | Applications, Benefits and Challenges of RL | Summary | Exercises
Chapter 10: Deep Learning Introduction | Fundamentals of Neural Networks | Artificial Neural Networks | Training Deep Neural Networks | Key Deep Learning Architectures | Future Direction of Deep Learning | Summary | Exercises
Chapter 11: Generative Artificial Intelligence: Large Language Models and Transformer-Based Architectures Introduction | Historical Development and Evolution of LLMs | Components of Transformer Architecture | Benefits of Transformer Architecture | Training Large Language Models | Types of Large Language Models | Advanced Topics in Large Language Models | Architecture of ChatGPT | Future Directions of Large Language Models | Applications of Generative AI | Challenges and Limitations of Large Language Models | Summary | Exercises
Chapter 12: Advanced Topics in Artificial Intelligence Introduction to Advanced Topics | Agentic AI | Explainable AI | Computer Vision | Conversational AI | Human–Robot Interaction | Future Trends | Summary | Exercises
Chapter 13: Ethics and Artificial Intelligence Introduction | Definition of Morality and Ethics in AI | Impact of AI on Society | Ethical Initiatives in AI | AI Standards and Regulation | Roboethics: The Social and Ethical Implications of Robotics | National and International Strategies on AI | Summary | Exercises
Chapter 14: Applications of Artificial Intelligence Introduction | The Evolution of Natural Language Processing | AI Applications in Robotics | AI Applications in Healthcare | AI Applications in Retail | AI Applications in Banking | Summary | Exercises
Chapter 15: Artificial Intelligence Programming Using Jupyter Notebook Introduction | Using the Online Interface of Jupyter Notebook | Experimentation Guidelines for Some AI Techniques | Python Program that Demonstrates the Use of Data Types | Python Program that Asks for User Input and Uses Conditional Statements to Respond with Different Outputs | Python Program that Prints Out a Sequence of Numbers using a for Loop and then Asks the User to Do the Same with a while Loop | Python Program that Defines a Function to Calculate the Area of a Circle, Given its Radius, and then Calls that Function with Different Values | Python Program that Creates a List of Items and a Dictionary of Key–Value Pairs, and then Demonstrates How to Access and Modify Elements | Python Program that Reads a Text File, Counts the Number of Words, and Writes the Result to a New File | Python Program that Intentionally Raises an Error and then Catches it with a try-except Block, Printing an Informative Message to the User | Python Program to Define a Class with Attributes and Methods to Demonstrate OOP | Python Program to Use the Matplotlib Library to Plot a Graph based on the Given Data Points and Enhance the Graph with Labels and a Legend | Python Program to Introduce the pandas Library by Creating a DataFrame from a Dictionary, and Performing Basic Data Manipulation Operations such as Sorting and Filtering | Python Program to Develop PEAS Descriptions for the Given AI Tasks | Python Program for the Uninformed Search Algorithm: Breadth-first Search (BFS) | Python Program for the Uninformed Search Algorithm: Depthfirst Search (DFS) | Python Program for the Informed Search Algorithm: A* Search with Heuristic Function | Python Program to Implement the AO* Algorithm | Python Program to Implement Memory-bounded A* Algorithms | Python Program to Implement Genetic Algorithms for AI Tasks | Python Program to Implement Local Search Technique: Hill Climbing Algorithm | Python Program to Implement Simulated Annealing Algorithms for AI Tasks | Python Program to Implement Game Playing Algorithms: Minimax | Python Program to Implement the Monkey and Banana Problem | Python Program to Implement the 8-Puzzle Problem | Python Program to Implement the Water Jug Problem | Python Program to Implement the Alpha–beta Pruning Algorithm | Python Program to Implement Backtracking Algorithms for CSP | Python Program to Implement the Local Search Algorithm for CSP | Python Program to Implement Propositional Logic Inferences for AI Tasks | Python Program to Implement Resolution based on First-order Logic Inferences for AI Tasks | Python Program to Conduct a Game Search | Python Program to Implement Tower of Hanoi | Python Program to Construct a Bayesian Network from the Given Data | Python Program to Infer from a Bayesian Network | Python Program for Value and Policy Iteration in a Grid World | Python Program to Perform Reinforcement Learning in a Grid World | Python Program to Implement a Chatbot | Python Program to Implement the N-Queens Problem | Python Program to Implement the Missionaries–Cannibals Problems | Summary | Exercises
Chapter 16: Prolog Programming The Role of Prolog in AI Programming | SWI-Prolog in Prolog Programming | Overview of SWI-Prolog Online | Basic Prolog Program on Ancestor Identification | Prolog Program for Parent–Child Relationships | Prolog Program for Logical and Descriptive Relationships | Prolog Program for Family Tree using Facts and Rules | Prolog Program for Data Objects | Prolog: Comparison Operators | Prolog: Arithmetic Operators | Prolog: Loops | Prolog Program for Decision Making using Conditional Rules | Prolog: Conjunctions and Disjunctions | Prolog Program to Work with Lists | Prolog Recursion and Structures | Prolog: Backtracking | Prolog: Different and Not | Prolog Program to Read and Write Data | Prolog Program to Read and Write Files | Prolog Program to Demonstrate Built-in Predicates | Prolog Program to Identify Terms | Prolog Program to Decompose Structures | Prolog Program to Collect All Solutions | Prolog Program for Tree Data Structure | Extended Program to Implement a Binary Tree with Pathfinding | Extended Program to Implement a Binary Tree with Node Location | Program to Find the Height of a Binary Tree | Prolog: Linked Lists | Prolog: Tower of Hanoi Problem | Prolog: Monkey and Banana Problem | Prolog: Tic-Tac-Toe | Prolog: Nim | Prolog: Advanced Version of Nim | Prolog: 8-Puzzle Problem | Prolog: Connect Four | Prolog: Sudoku Solver | Prolog: Minesweeper | Prolog: The Knight’s Tour | Summary
Index