Course Outline: Machine Learning
Instructor: Mohammad Sakib Mahmood
Department of Computer Science
University of Development Alternative
July 20, 2025
Course Duration: 10 Weeks
Level: Undergraduate (Theory Focused)
Mode of Delivery: Lecture-based (Conceptual with real-world illustrations)
Course Objective:
This course aims to introduce students to the fundamental principles of machine learning,
focusing on theoretical understanding of key algorithms and techniques. Students will ex-
plore core concepts in supervised and unsupervised learning, evaluate model performance,
and examine the ethical implications of machine learning in society.
Weekly Course Breakdown
Week 1: Introduction to Machine Learning
• Definition and scope of Machine Learning
• Differences between AI, ML, and Deep Learning
• Categories of Learning: Supervised, Unsupervised, Reinforcement
• Applications of Machine Learning across domains
• Overview of a typical ML project lifecycle
Week 2: Linear Regression
• Fundamentals of regression analysis
• Least Squares Estimation
• Mean Squared Error (MSE) as a cost function
1
• Introduction to Gradient Descent optimization
• Understanding underfitting and overfitting
Week 3: Classification and Logistic Regression
• Binary classification problems and model formulation
• Logistic function and decision boundaries
• Cross-entropy loss for classification
• Performance metrics: Accuracy, Precision, Recall, F1-Score
• Use cases of logistic regression
Week 4: Data Preprocessing and Feature Engineering
• Role of data preprocessing in ML
• Handling missing and noisy data
• Encoding categorical variables
• Feature scaling techniques
• Introduction to dimensionality reduction (PCA)
Week 5: Decision Trees and Ensemble Methods
• Decision Tree structure and splitting criteria
• Overfitting, pruning techniques, and tree depth
• Introduction to ensemble learning
• Overview of Random Forests
• Concepts of Bagging and Boosting
Week 6: Naive Bayes and Probabilistic Learning
• Fundamentals of probability and conditional probability
• Application of Bayes’ Theorem in classification
• Assumptions and structure of the Naive Bayes Classifier
• Practical applications: spam filtering, text classification
2
Week 7: Support Vector Machines (SVM)
• Concept of separating hyperplanes and margin maximization
• Support vectors and optimal decision boundaries
• Soft margin and hard margin classifiers
• Conceptual understanding of the kernel trick
Week 8: Clustering and Unsupervised Learning
• Introduction to unsupervised learning techniques
• K-Means Clustering: algorithm, convergence, and initialization
• Choosing the number of clusters (Elbow Method)
• Overview of hierarchical clustering techniques
Week 9: Neural Networks and Deep Learning
• Historical context and biological inspiration
• Structure and function of a perceptron
• Activation functions: Sigmoid, ReLU
• Forward pass concept (overview only)
• Applicability and challenges of neural networks
Week 10: Challenges, Ethics, and Emerging Trends in ML
• Fairness, accountability, and transparency in ML systems
• Explainability and model interpretability
• Overfitting, generalization, and data biases
• Overview of current trends: AutoML, Generative AI, Responsible AI
• Future directions and interdisciplinary applications
3
Recommended Textbooks
1. Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and Ten-
sorFlow, O’Reilly Media
2. Oliver Theobald, Machine Learning for Absolute Beginners, Independent Pub-
lishing
