Elective Foundations of Artificial Intelligence

This folder contains study material for the first-semester Artificial Intelligence elective.

The five module notes have been expanded against the 87 source PDFs in PdfMaterial/Eelective Artifical Intilegence. The module files now include the definitions, assumptions, formulas, algorithms, worked-problem procedures, and limitations needed for revision. Use the original PDFs only when you need the source diagrams or additional illustrations.

The modules use a campus delivery robot as a recurring example: it perceives campus paths, searches for routes, represents buildings and constraints, reasons about uncertain travel time, and learns from completed deliveries.

Module-wise study method

1. Review prerequisites and complete one 10-15-minute study block.
2. Draw or trace the agent, search tree, representation, probability model, or network.
3. Calculate one small example manually before using code.
4. Attempt the mini quiz and practice ladder before revealing solutions.
5. Mark the module Mastered after solving a new campus-robot scenario without notes.

Course Modules

Module	Title	Minimum Time
1	Introduction to AI	1 week
2	Problem Spaces and Search	1 week
3	Knowledge Representation	1 week
4	Uncertain Knowledge and Reasoning	1 week
5	Artificial Neural Networks	1 week

Module 1 - Introduction to AI

1. Introduction to AI Concepts - Part 1
2. Introduction to AI Concepts - Part 2.1
3. Introduction to AI Concepts - Part 2.2
4. AI Environments - Part 1
5. AI Environments - Part 2
6. Intelligent Agents

Module 2 - Problem Spaces and Search

1. Uninformed Searches - Part 1
2. Uninformed Searches - Part 2
3. Informed Searches - Part 1.1
4. Informed Searches - Part 1.2
5. Informed Searches - Part 2
6. Informed Searches - Part 3
7. CSP and Adversarial Search - Part 1.1
8. CSP and Adversarial Search - Part 1.2
9. CSP and Adversarial Search - Part 2
10. Informed Searches - Part 3 Practice Session
11. Problem Reduction
12. Uninformed Searches - Practical Session 1
13. Uninformed Searches - Practical Session 2
14. Informed Searches - Practical Session 2
15. Informed Searches - Part 2 Practice Session
16. Informed Searches - Part 1 Practice Session
17. Uninformed Searches - Practice Session 3
18. Uninformed Searches - SSR Problem Solving Part 1
19. Uninformed Searches - SSR Problem Solving Part 2
20. Uninformed Searches - Problem Solving: Searching Part 1
21. Uninformed Searches - Problem Solving: Searching Part 2
22. Uninformed Searches - Problem Solving: Searching Part 3
23. Uninformed Searches - Problem Solving: Searching Part 4
24. Uninformed Searches - Problem Solving: Searching Part 5

Module 3 - Knowledge Representation

1. Approaches to Knowledge Representation - Introduction to KR Part 1
2. Approaches to Knowledge Representation - Introduction to KR Part 2
3. Structured Knowledge Representation - Introduction to KR Part 3.1
4. Structured Knowledge Representation - Introduction to KR Part 4
5. Slot and Filler Structures - Introduction to KR Part 5
6. Slot and Filler Structures - Introduction to KR Part 6
7. Weak Structures - Semantic Nets as a KR Method Part 1
8. Strong Structures - Conceptual Dependency as KR Part 1
9. Ontological Engineering - Knowledge Graphs and Ontology Part 1.1
10. Propositional Logic as a KR Method - Part 1
11. Propositional Logic as a KR Method - Part 3.1 Practice Session
12. Weak Structures - Semantic Nets as a KR Method Part 2
13. Weak Structures - Partitioned Semantic Nets as a KR Method
14. Ontological Engineering - Knowledge Graphs and Ontology Part 2
15. Propositional Logic as a KR Method - Part 3.2 Practice Session
16. Structured Knowledge Representation - Introduction to KR Part 3.2
17. Strong Structures - Conceptual Dependency as KR Part 2.1
18. Strong Structures - Conceptual Dependency as KR Part 3
19. Ontological Engineering - Knowledge Graphs and Ontology Part 1.2
20. Strong Structures - Conceptual Dependency as KR Part 2.2
21. Weak Structures - Frames in KR Part 1
22. Weak Structures - Frames in KR Part 2
23. Weak Structures - Partitioned Semantic Nets as a KR Method
24. Propositional Logic as a KR Method - Part 2

Module 4 - Uncertain Knowledge and Reasoning

1. Acting Under Uncertainty - Part 1.1
2. Independence - Part 1
3. Bayes Rule - Part 1.1
4. Time and Uncertainty - Part 1
5. Acting Under Uncertainty - Part 1.2
6. Bayes Rule - Part 1.2
7. Acting Under Uncertainty - Part 3
8. Acting Under Uncertainty - Part 2
9. Time and Uncertainty - Part 2
10. Independence - Part 2
11. Hidden Markov Models - Part 1
12. Bayes Rule - Part 2
13. Naive Bayes Model - Part 1
14. Bayes Rule - Part 3
15. Naive Bayes Model - Part 2
16. Naive Bayes Model - Part 3
17. Naive Bayes Model - Part 4 Practice Session
18. Hidden Markov Models - Part 2
19. Hidden Markov Models - Part 3 Practice Session

Module 5 - Artificial Neural Networks

1. Introduction to Neural Networks - Neuron Abstraction Part 1.1
2. Introduction to Neural Networks - Neuron Abstraction Part 1.2
3. Neuron Signal Functions - Part 1
4. Neuron Signal Functions - Part 2
5. Architectures and Applications: Learning Algorithms Part 3.1
6. Gradient Descent Algorithm - Part 2
7. Perceptron Learning - Part 1.1
8. Gradient Descent Algorithm - Part 1
9. Gradient Descent Algorithm - Practice Session
10. Neural Network Using Perceptron - Part 1.1 Practice Session
11. Neural Network Using Perceptron - Part 1.2 Practice Session
12. Neural Network Using Perceptron - Part 2.1 Practice Session
13. Neural Network Using Perceptron - Part 2.2 Practice Session
14. Neural Network Using Perceptron - Part 2.3 Practice Session
15. Backpropagation - Practice Session Part 2
16. Backpropagation - Practice Session Part 4
17. Architectures and Applications: Learning Algorithms Part 3.2
18. Perceptron Learning - Practice Session Part 2
19. Perceptron Learning - Part 1.2
20. Feedback Architecture and Backpropagation Algorithm - Part 3
21. Neural Network Using Perceptron - Part 3 Practice Session
22. Introduction to Neural Networks - Neuron Abstraction Part 1.3
23. Feedback Architecture and Backpropagation Algorithm - Part 1

Revision Material

• Quick Revision - module-by-module last-minute review.
• Cheat Sheet - algorithms, formulas, and comparison tables.
• Important Questions - graded university questions.
• MCQ - multiple-choice practice by module.
• Glossary - important AI terms in alphabetical order.
• Web Resources - trusted resources for second explanations.

Suggested Study Order

1. Learn the concepts in each module in the listed order.
2. Work through the practical and problem-solving sessions immediately after the related theory.
3. Use the MCQ question bank for revision after completing all five modules.

Progress guidance

For each module, mark your status as Not Started, Learning, Needs Revision, or Mastered. Do not mark a module mastered until you can solve its worked example and answer at least four of its five review questions without notes.