Machine Learning (EC 332) - Department of Computer Science

Course Title: Machine Learning
Course Code: EC 332
Credits: 3
Instructor: Dr. Nazar Khan
Semester: Spring 2025
Location: FCIT, Allama Iqbal Campus, Room 9
Class Times: Tuesdays and Thursdays, 2:15 PM - 3:45 PM
Join Google Classroom 		Textbook:
Deep Learning: Foundations and Concepts (Bishop)
by Chris Bishop and Hugh Bishop.
Springer Nature
2024
dlfaccover 		Reference Books:
  1. Machine Learning: A Probabilistic Perspective (Murphy), Kevin P. Murphy, MIT Press, 2022.
  2. Reinforcement Learning: An Introduction (Sutton), 2nd Edition, Richard S. Sutton and Andrew G. Barto, MIT Press, 2018.
  3. Data Mining and Machine Learning: Fundamental Concepts and Algorithms (Zaki), 2nd Edition, Mohammed J. Zaki, Wagner Meira, Jr., Cambridge University Press, 2020.

dlfaccover
dlfaccover
dlfaccover

Welcome to the Machine Learning course page! Machine learning is a field of AI that focuses on the development of algorithms that can learn from and make predictions on data. In this course, you will study both the theoretical underpinnings and practical applications of machine learning techniques. This course covers the theory and practice of supervised learning, unsupervised learning, neural networks, deep learning, and reinforcement learning.

Lectures

Lecture No. Topics Covered Reading Material Quiz/Assign./H.W./Project
1 Introduction to Machine Learning
Introduction to Neural Computation 		Bishop 1.1
2 Brief History of Machine Learning Bishop 1.3
3 Curve Fitting Bishop 1.2 Tutorial 1: Linear Regression
4 Rules of Probability Bishop 2.1
5 Gaussian Distribution and Maximum-Likelihood Bishop 2.3, 3.2, 4.1 Tutorial 2: Gaussian Density Estimation
6 Neural Networks Bishop 6.3
7 Loss Functions for Machine Learning Bishop 6.4
8 Gradient Descent - I Bishop Ch 7
9 Gradient Descent - II Bishop Ch 7
10 Backpropagation Bishop 8.1
11 Automatic Differentiation Bishop 8.2 Tutorial 3: Neural Network using PyTorch
Mid-term Exam
13 Regularization Bishop Ch 9
14 Convolutional Neural Networks (CNNs) Bishop 10.2 Assignment 1
15 Applications of CNNs Bishop 10.4, 10.5, 10.6
16 Transformers Bishop 12.1
17 Transformer Language Models Bishop 12.2, 12.3 Tutorial 4: Sentiment Classification using a Transformer
Assignment 2
18 K-Means Clustering Bishop 15.1 Tutorial 5: K-Means Clustering with Automatic Estimattion of K
19 Gaussian Mixture Models Bishop 15.2 Assignment 3
20 DBSCAN Zaki 15.1 Tutorial 6: Clustering via DBSCAN
Project 1
21 Principal Component Analysis Bishop 16.1 Tutorial 7: Face Recognition via PCA
22 Generative Adversarial Networks Bishop Ch 17
23 Reinforcement Learning: Q-Learning
UntrainedTrained
Slides Tutorial 8: CartPole Balancing using Q-Learning, (HTML, PDF)
Untrained agent, Trained agent
24 Deep Q-Learning
UntrainedTrained
Slides Tutorial 9: CartPole Balancing using Deep Q-Learning, (HTML, PDF)
Untrained DQN agent, Trained DQN agent
25 Bandit Problems vs QL DQL Slides
Final-term Exam

Grading

Assignments Project Quizzes Midterm Exam Final Exam
Weight 12% 8% 5% 35% 40%