Artificial Intelligence, As per AICTE: Making a System Intelligent | Dr. Nilakshi Jain | Wiley

Artificial Intelligence: Making a System Intelligent explains concept of intelligent systems, techniques from knowledge-based systems, neural networks, fuzzy systems, evolutionary computation, and intelligent agents. The principles behind these techniques have been explained in this book without resorting to complex mathematics. The lack of assumed prior knowledge makes this book ideal for any introductory course in artificial intelligence or intelligent systems design. The contemporary coverage of this book is highly beneficial to advanced students as it facilitates in discovering state-of-the-art techniques, particularly in intelligent agents and knowledge discovery.

Contents 

1 Introduction to Artificial Intelligence 1.1 Introduction 1.2 Definition of AI 1.3 Goals of AI 1.4 Abridged History and Foundation of AI 1.5 Branches or Subareas of AI 1.6 Applications of AI 1.7 Categorization of AI 1.8 Components of AI 1.9 Current Trends in AI 1.10 AI Programming Languages

2 Intelligent Agents 2.1 Introduction 2.2 Intelligent Systems 2.3 The Concept of Rationality 2.4 Types of Agents 2.5 Environments and Its Properties 2.6 PEAS Representation for an Agent 2.7 Intelligent Agent Application

3 Problem Solving 3.1 Introduction to Problem Solving 3.2 Problem Formulation 3.3 State–Space Representation 3.4 Problem Formulation of the Eight Tile Puzzle 3.5 Problem Formulation of Water Jug Problem 3.6 Problem Formulation Vacuum Cleaner World Problem 3.7 Problem Formulation of Wumpus World Problem 3.8 Problem Formulation of Missionaries and Carnivals Problem 3.9 Production System 3.10 Difference between Conventional Problems and AI Problems 3.11 Searching 3.12 Problem Characteristics and Issues in the Design of Search Programs 3.13 Solving Problems by Searching 3.14 Types of Search Strategies

4 Uninformed Search Strategies 4.1 Introduction 4.2 Brute Force or Blind Search 4.3 Breadth-First Search 4.4 Depth-First Search 4.5 Difference between BFS and DFS 4.6 Uniform Cost Search 4.7 Depth-Limited Search 4.8 Iterative Deeping DFS 4.9 Bidirectional Search 4.10 Comparing Uniform Search Strategies

5 Informed Search 5.1 Introduction 5.2 Hill Climbing 5.3 Best-First Search (Greedy Search) 5.4 A* Search 5.5 AO* Search: (AND–OR) Graph 5.6 Memory Bounded Heuristic Search 5.7 Simulated Annealing Search 5.8 Local Beam Search 5.9 Branch and Bound Search

6 Adversarial Search 6.1 Introduction 6.2 Optimal Strategies 6.3 The Minimax Algorithm 6.4 Alpha–Beta Pruning

7 Constraint Satisfaction Problem 7.1 Introduction 7.2 General Form of the CSP 7.3 Map Colouring Problem 7.4 N-Queens Problem 7.5 N-Queens Problem Formulation 7.6 Forward Checking 7.7 Crypto Arithmetic Problem

8 Knowledge and Reasoning 8.1 A Knowledge-Based Agent 8.2 The Wumpus World 8.3 Knowledge Representation Issues

9 Predicate Logic 9.1 Representation of Simple Fact in Logic 9.2 Representing Instance and Is_A Relationship in Predicate Logic 9.3 Computable Functions and Predicate Logic 9.4 Resolution 9.5 Knowledge Engineering in First-Order Logic 9.6 Unification 9.7 Natural Deduction

10 Representation Knowledge Using Rules 10.1 Propositional Logic 10.2 Frist-Order Logic/Predicate Logic 10.3 Inference in First-Order Logic 10.4 Procedural versus Declarative Knowledge 10.5 Logic Programming 10.6 Forward and Backward Reasoning 10.7 Matching 10.8 Control Knowledge 10.9 Forward and Backward Chaining (Type of Reasoning)

11 Planning and Learning 11.1 Introduction 11.2 The Language of Planning Problems 11.3 Planning with State Space Search 11.4 Partial Ordered Planning 11.5 Hierarchical Planning 11.6 Conditional Planning 11.7 Learning Introduction 11.8 Forms of Learning 11.9 Inductive Learning 11.10 Learning Decision Trees 11.11 Ensemble Learning 11.12 Reinforcement Learning

12 Uncertain Knowledge and Reasoning 12.1 Uncertainty 12.2 Basic Probability Theorem 12.3 Joint Probability 12.4 Baye’s Theorem 12.5 Representing Knowledge in an Uncertain Domain (Bayesian Belief Network) 12.6 Simple Inference in Belief Network 12.7 Temporal Model 12.8 Markov Decision Process

13 Natural Language Processing 13.1 Introduction 13.2 Exponential 13.3 Natural Language for Communication 13.4 Syntactic Analysis 13.5 Argumented Grammar 13.6 Semantic Interpretation

14 Expert System 14.1 Expert System 14.2 Need and Justification of ES 14.3 Knowledge Representation 14.4 Knowledge Acquisition and Variation 14.5 Utilisation and Functionality 14.6 Basics of Prolog

15 Application 15.1 Introduction 15.2 Category of Applications of AI 15.3 Robotics 15.4 Artificial Neural Network 15.5 AI Trends in Various Sectors 15.6 More About Agents of AI

16 Cognitive Computing 16.1 Introduction 16.2 Foundation of Cognitive Computing 16.3 List of Design Principles for Cognitive Systems 16.4 Natural Language Processing in Support of a Cognitive System

17 Introduction to Soft Computing and Fuzzy Logic 17.1 Introduction 17.2 Soft Computing versus Hard Computing 17.3 Various Types of Soft and Hard Computing Techniques 17.4 Fuzzy Logic 17.5 Fuzzy Set versus Crisp Set 17.6 Membership Function 17.7 Fuzzy Rules 17.8 Fuzzy Reasoning 17.9 Fuzzy Inference System 17.10 Fuzzification 17.11 Defuzzification 17.12 Fuzzy Controllers

18 Artificial Neural Network 18.1 Introduction to Artificial Neural Networks 18.2 Basic Models of Artificial Neural Networks 18.3 First Artificial Neurons: McCulloch–Pitts Model 18.4 Neural Network Architecture 18.5 Single-Layer Feedforward ANN 18.6 Multilayer Feedforward ANN 18.7 Activation Functions 18.8 Supervised Learning 18.9 Delta Learning Rule 18.10 Backpropagation Algorithm 18.11 Unsupervised Learning Algorithm 18.12 Self-Organising Maps 18.13 Hybrid Approach: Fuzzy Neural Systems

Summary, Review Questions, Short-Type Questions, Multiple-Choice Questions, Answers

About the Author

Dr. Nilakshi Jain currently serves as an Associate Professor at the Shah & Anchor Kutchhi Engineering College in the Information Technology Department, Mumbai, India. She is the Research Coordinator of SAKEC Research Cell and President of Institution Innovation Council. She is a Certified Ethical Hacker CEH (EC-Council- USA). She has a rich experience of working in the Digital Forensic field. Her areas of research include Artificial Intelligence, Human Computer Interaction, and Usability Engineering.