Artificial Intelligence
Artificial Intelligence
The University of Modern Sciences, Tando Muhammad Khan, Sindh
Instructor: Prof. Dr. Mudasar Latif Memon
Ph.D. in Electronic & Electrical Engineering (Applied AI)
Professor of Applied Artificial Intelligence
Course Code: ITEC-518
Credit Hours: 3(3+0) - Theory + Practical
Semester: 5th (BS IT)
Prerequisites: Data Structures, Programming Fundamentals, Discrete Mathematics
This course provides a comprehensive introduction to Artificial Intelligence, covering fundamental concepts, techniques, and applications. Students will learn about intelligent agents, search algorithms, knowledge representation, machine learning, and modern AI applications. The course combines theoretical foundations with practical implementation to develop problem-solving skills using AI techniques.
By the end of this course, students will be able to:
Understand fundamental concepts and history of Artificial Intelligence
Design and implement intelligent agents for various problem domains
Apply search algorithms (uninformed and informed) to solve complex problems
Utilize knowledge representation techniques and reasoning mechanisms
Implement machine learning algorithms for classification and prediction
Develop solutions using neural networks and deep learning fundamentals
Apply AI techniques to real-world problems in healthcare, business, and technology
Understand ethical implications and societal impact of AI systems
CLO-1: Comprehend the theoretical foundations of artificial intelligence including intelligent agents, problem-solving approaches, and knowledge representation
CLO-2: Apply search algorithms, optimization techniques, and reasoning methods to solve AI problems
CLO-3: Design and implement machine learning models and neural networks for practical applications
CLO-4: Evaluate and critically analyze AI systems considering ethical, social, and technical perspectives
What is AI? History and Evolution
Applications of AI in Modern World
Types of AI: Weak vs Strong AI
AI in Pakistan and Global Context
Lab: Setting up Python environment, Introduction to AI libraries (lecture_1)
Agent and Environment
PEAS Description
Agent Types: Simple Reflex, Model-based, Goal-based, Utility-based
Rational Agents and Performance Measures
Lab: Implementing Simple Reflex Agents in Python
Problem Formulation
State Space Representation
Uninformed Search: BFS, DFS, DLS
Complexity Analysis
Lab: Implementing BFS and DFS algorithms
Informed Search: Greedy Best-First Search
A* Search Algorithm
Heuristic Functions
Admissibility and Consistency
Lab: Implementing A* Search for pathfinding problems
Game Playing in AI
Minimax Algorithm
Alpha-Beta Pruning
Monte Carlo Tree Search (Introduction)
Lab: Creating a Tic-Tac-Toe game with Minimax
CSP Formulation
Backtracking Search
Forward Checking and Arc Consistency
Applications: N-Queens, Sudoku
Lab: Solving Sudoku using CSP techniques
Propositional Logic
First-Order Logic (FOL)
Inference in Logic
Semantic Networks and Frames
Lab: Implementing logical inference systems
Theory Exam (Week 1-7)
Practical Assessment
Probability Theory in AI
Bayesian Networks
Inference in Bayesian Networks
Hidden Markov Models (Introduction)
Lab: Building simple Bayesian Networks
Types of Learning: Supervised, Unsupervised, Reinforcement
Linear Regression
Logistic Regression
Model Evaluation Metrics
Lab: Implementing Linear and Logistic Regression
Decision Trees
K-Nearest Neighbors (KNN)
Naive Bayes Classifier
Support Vector Machines (Introduction)
Lab: Implementing classification algorithms on datasets
K-Means Clustering
Hierarchical Clustering
Principal Component Analysis (PCA)
Applications in Data Analysis
Lab: Implementing clustering algorithms
Biological Neurons vs Artificial Neurons
Perceptron Algorithm
Multi-Layer Perceptrons (MLP)
Backpropagation Algorithm
Lab: Building neural networks from scratch
Deep Neural Networks
Convolutional Neural Networks (CNN) - Basics
Recurrent Neural Networks (RNN) - Overview
Transfer Learning Concept
Lab: Using TensorFlow/Keras for image classification
Natural Language Processing (NLP) Basics
Computer Vision Applications
AI in Healthcare (Medical Diagnosis, Ultrasound Analysis)
Recommender Systems
Lab: Building a simple chatbot or image classifier
Ethical Considerations in AI
Bias and Fairness
AI Safety and Alignment
Future of AI: AGI, Quantum AI
Career Opportunities in AI
Lab: Project presentations
Theory Final Exam
Practical Final Exam
Project Submission and Evaluation
Component
Weightage
Assignments
10%
Quizzes
10%
Lab Work/Practicals
10%
Mid-Term Exam
25%
Final Project
15%
Final Exam
30%
Total
100%
Primary:
Stuart Russell & Peter Norvig, "Artificial Intelligence: A Modern Approach" (4th Edition), Pearson
Ethem Alpaydin, "Introduction to Machine Learning" (3rd Edition), MIT Press
Secondary:
Ian Goodfellow et al., "Deep Learning", MIT Press
Tom Mitchell, "Machine Learning", McGraw-Hill
Francois Chollet, "Deep Learning with Python" (2nd Edition)
Programming Language: Python 3.x
Development Environment: Jupyter Notebook, Google Colab, VS Code
Libraries: NumPy, Pandas, Matplotlib, Scikit-learn
Deep Learning: TensorFlow, Keras, PyTorch (Introduction)
Tools: Git/GitHub for version control
Students will work in groups (3-4 members) to develop an AI application addressing a real-world problem. Project domains include:
Healthcare: Disease prediction, medical image analysis
Agriculture: Crop disease detection, yield prediction
Education: Intelligent tutoring systems
Business: Customer churn prediction, sentiment analysis
Smart cities: Traffic prediction, energy optimization
Project Milestones:
Week 8: Project proposal submission
Week 12: Mid-project presentation
Week 16: Final presentation and code submission
Minimum 75% attendance is mandatory
More than 3 unexcused absences may result in grade penalty
Late arrivals (>15 minutes) count as 0.5 absence
Plagiarism in assignments/projects will result in zero marks
Collaboration is encouraged, but submissions must be individual
Proper citation required for all external resources
Use of AI tools (ChatGPT, etc.) must be disclosed and properly attributed
Available for consultation after class or by appointment via email.
Course content may be adjusted based on class progress
Guest lectures from industry professionals will be arranged
Field visits to tech companies in Karachi may be organized
Special focus on AI applications relevant to Pakistani context and rural development