Course Objectives

The objective of this course is to build a strong foundation in Artificial Intelligence (AI), covering intelligent agents, search techniques, knowledge representation, machine and learning. It aims to equip students with both theoretical knowledge and practical skills to apply AI techniques in solving real-world problems, while also fostering awareness of the ethical considerations associated with AI applications.

Course Contents

1. Introduction

4 hrs

1.1. Definition, foundation, history of AI

1.2. AI tree: Branches and interdisciplinary nature

1.3. Definition and importance of knowledge and learning

1.4. Human intelligence and machine intelligence

1.5. Intelligent agents and types

2. Problem Solving and Search

9 hrs

2.1. Formal problem definition: States, actions, transitions, well-defined problems

2.2. Constraint satisfaction problems: Node consistency, path consistency, backtracking

2.3. Search algorithms, strategies, and evaluations

2.4. Uninformed: BFS, DFS, iterative deepening

2.5. Informed search: Best first search, greedy search, A* algorithm

2.6. Adversarial search: Minimax algorithm, alpha-beta pruning

2.7. Local search and optimization: Hill climbing, simulated annealing

2.8. Evolutionary optimization: Genetic algorithm

3. Knowledge Representation and Probabilistic Reasoning

7 hrs

3.1. Knowledge-based agent

3.2. Knowledge representation techniques and issues in representation

3.3. Propositional and predicate logic

3.4. Semantic networks and frames

3.5. Probabilistic reasoning, inference using Bayes' theorem

3.6. Fuzzy logic: Membership functions, fuzzy inference systems

4. Machine Learning Fundamentals

10 hrs

4.1. Forms of learning: Supervised, unsupervised, semi-supervised, reinforcement learning

4.2. Machine learning pipeline

Preprocessing and cleaning

Model development

Training, testing, and hyperparameter tuning

4.3. Overfitting, underfitting, bias-variance tradeoff

4.4. Regression and classification with linear model

4.5. Classification using decision tree and Naive Bayes

4.6. Evaluation with confusion matrix

5. Neural Networks and Deep Learning Algorithms

6 hrs

5.1. Neural networks: Structures and activation functions

5.2. Perceptron, multilayer perceptron, and backpropagation

5.3. Introduction to deep learning

5.4. Concepts on recurrent and generative neural networks

6. AI Applications

7 hrs

6.1. Expert systems: Characteristics, architecture, development and various applications

6.2. NLP: Level of analysis and application

6.3. Robotics and computer vision: Fundamental, components and applications

6.4. VLSI testing, fault diagnosis, and sustainable systems

7. AI Ethics and Recent Trends

2 hrs

7.1. Responsible AI: Bias, fairness, explainability

7.2. Ethical and societal considerations

7.3. Privacy and security in AI

7.4. Emerging trends: Federated learning, embedded AI

Laboratory Works

Students will perform hands-on practical exercises covering knowledge-based agents and search, adversarial search and CSP, symbolic and probabilistic reasoning, supervised and unsupervised machine learning, neural networks basics, and a mini project on AI applications.

1.Knowledge-based agents and search
2.Adversarial search and CSP
3.Symbolic and probabilistic reasoning
4.Machine learning – Supervised and unsupervised
5.Neural networks basics
6.Mini project and AI applications

Reference Books

1.Russell, S., Norvig, P. (2020). Artificial intelligence: A modern approach. Pearson.
2.Rich, E., Knight, K., Nair, S. B. (2009). Artificial intelligence. McGraw-Hill.
3.Bishop, C. M. (2006). Pattern recognition and machine learning. Springer.
4.Deisenroth, M. P., Faisal, A. A., Ong, C. S. (2020). Mathematics for machine learning. Cambridge University Press.

Artificial Intelligence

Artificial Intelligence

Select University

Select Program

TabFlux . Artificial Intelligence . TU . BEI