Course Information
Artificial Intelligence is one of the most important disciplines of Computer Science, covering intelligent problem solving, knowledge representation, reasoning, machine learning, planning, natural language processing, computer vision and intelligent agents. This page follows the organization of the Springer Nature book Fundamentals of Artificial Intelligence.
Book Information
- Author: Prof. K. R. Chowdhary
- Publisher: Springer Nature
- Book: Fundamentals of Artificial Intelligence
Learning Outcomes
- Understand the principles and foundations of Artificial Intelligence.
- Represent knowledge using logic, rules and semantic structures.
- Design intelligent search and reasoning algorithms.
- Develop AI applications using machine learning techniques.
- Apply planning, data mining, NLP, speech recognition and computer vision methods.
- Acquire the background needed for advanced AI research and industrial applications.
Prerequisites
- Programming in C/C++ or Python
- Discrete Mathematical Structures
- Data Structures and Algorithms
- Probability and Statistics (desirable)
Course Contents
This course provides a comprehensive introduction to Artificial Intelligence, covering both its theoretical foundations and modern applications. Beginning with knowledge representation, logical reasoning and search techniques, it progresses through machine learning, planning, intelligent agents, data mining, natural language processing, speech recognition and computer vision. The course emphasizes mathematical foundations, algorithms, worked examples, and practical applications, enabling students to understand how AI techniques are used to design intelligent systems for solving real-world problems.
The contents are organized into 10 teaching modules corresponding to the chapters of the Springer Nature book Fundamentals of Artificial Intelligence, allowing the course to be used for undergraduate, postgraduate and self-learning programmes.
Course Modules
Module 1: Foundations of Artificial Intelligence
Chapter 1: Introduction to Artificial Intelligence
Introduction to AI, intelligent systems, history, goals of AI, Turing Test, symbol systems, knowledge representation, engineering applications and future directions of Artificial Intelligence.
Module 2: Logic and Automated Reasoning
Chapter 2: Logic and Reasoning Patterns
Logical foundations of AI including propositional logic, syntax, semantics, reasoning, semantic tableaux, normal forms, resolution, and non-monotonic reasoning.
Chapter 3: First Order Predicate Logic
Predicate logic, quantifiers, clause forms, unification, resolution theorem proving, Herbrand universe, most general unifier and knowledge representation.
Module 3: Rule-Based Systems and Logic Programming
Chapter 4: Rule-Based Reasoning
Forward and backward chaining, inference engines, rule selection, model-based reasoning, case-based reasoning and expert systems.
Chapter 5: Logic Programming and Prolog
Logic programming, facts, rules, recursion, control strategy, Prolog interpreters and AI programming examples.
Module 4: Knowledge Representation
Chapter 6: Real-World Knowledge Representation and Reasoning
Taxonomies, ontologies, commonsense reasoning, default reasoning, action and change, situation calculus and real-world knowledge.
Chapter 7: Networks-Based Representation
Semantic networks, conceptual graphs, frames, description logic, conceptual dependency and scripts.
Module 5: State Space and Heuristic Search
Chapter 8: State Space Search
State-space representation, breadth-first search, depth-first search, iterative deepening, bidirectional search and complexity analysis.
Chapter 9: Heuristic Search
Hill climbing, best-first search, A* search, simulated annealing, genetic algorithms and heuristic optimization.
Module 6: Constraint Satisfaction and Game Playing
Chapter 10: Constraint Satisfaction Problems
Constraint graphs, backtracking, constraint propagation, generate-and-test algorithms, cryptarithmetic and CSP applications.
Chapter 11: Adversarial Search and Game Theory
Game theory, minimax search, alpha-beta pruning, game strategies, zero-sum games and adversarial search.
Module 7: Reasoning Under Uncertainty
Chapter 12: Reasoning in Uncertain Environments
Probability theory, Bayesian reasoning, Bayesian networks, Dempster-Shafer theory, fuzzy sets and fuzzy inference.
Module 8: Machine Learning
Chapter 13: Machine Learning
Learning systems, supervised and unsupervised learning, decision trees, inductive learning, reinforcement learning, analogy, explanation-based learning and applications.
Chapter 14: Statistical Machine Learning
Support Vector Machines, k-nearest neighbours, Naïve Bayes classifiers, artificial neural networks, deep learning and instance-based learning.
Module 9: Automated Planning and Intelligent Agents
Chapter 15: Automated Planning
Classical planning, STRIPS, planning graphs, partial-order planning, hierarchical planning, planning languages and multi-agent planning.
Chapter 16: Intelligent Agents
Agent architectures, autonomous agents, mobile agents, communication languages, coordination, cooperation and coalition formation.
Module 10: Data Mining
Chapter 17: Data Mining
Knowledge discovery from large databases, classification, clustering, association rules, sequential pattern mining and scientific applications.
Module 11: Information Retrieval and Web Intelligence
Chapter 18: Information Retrieval
Vector space model, probabilistic retrieval, indexing, query expansion, semantic web, distributed information retrieval and Bayesian methods.
Module 12: Natural Language Processing and Speech Recognition
Chapter 19: Natural Language Processing
Natural language understanding, grammars, parsing, information extraction, question answering, commonsense reasoning and NLP tools.
Chapter 20: Automatic Speech Recognition
Speech recognition process, language and acoustic models, Hidden Markov Models, Kaldi, CMU-Sphinx, HTK and DeepSpeech.
Module 13: Computer Vision
Chapter 21: Machine Vision
Image understanding, computer vision, object recognition, 3-D reconstruction, object tracking, robot vision and vision applications.
Further Learning
The Springer book contains numerous worked examples, algorithms, illustrations, review questions and exercises, making it suitable for undergraduate, postgraduate and self-learning courses in Artificial Intelligence.