CSE-403 Machine Learning



E-mail: atik@cse.green.edu.bd

🕾 Mob. +8801912961096

:office: Room: A-510 Desk No. : 08

Class Routine – Summer 2026 Semester


Day 08:30-10:00 10:00-11:30 11:30-1:00 Break 1:30-03:00 3:00-4:30
Sat CSE 435
223_D1
K-105		 CSE 435
223_D1
K-105		     Tutor Time Research Meeting
Sun   CSE 403
232_D2
K-105		 Tutor Time   CSE 315
241_D2
K-108		 Research Meeting
Mon CSE 404
232_D4
L-106		 CSE 404
232_D4
L-106		 Research Meeting   CSE 310
Old Batch
A-502		 CSE 310
Old Batch
A-502
Tue CSE 315
241_D2
K-108		 CSE 403
232_D2
K-105		 Research Meeting   Tutor Time Tutor Time
Wed            



Topic Outline

Lecture Selected Topic Article / Materials Problems
(1-2) Introduction to Machine Learning; What is ML? Three Approaches: Supervised, Unsupervised, Reinforcement Learning Slides  
(3-4) Elements of a Supervised Learning Problem; Dataset and Learning Algorithm Overview Slides  
(5-6) Linear Regression: Concepts, Gradient Descent, Ordinary Least Squares, Regularization & Model Evaluation Slides, Math Notes, Math Notes CT 1
(7-9) Classification: Classification Basics, Logistic Regression, Softmax Regression, Multi-Class Classification, Regularization & Model Evaluation Slides, Math Notes, Math Notes Call for paper presentaions
(10-11) K-Nearest Neighbors, Naive Bayes Classifier Slides, Math Notes, Math Notes  
(12-13) Support Vector Machines (Linear & Nonlinear), Decision Trees (ID3) Slides, Math Notes, Math Notes Assignment 1
  Midterm Examination    
(14-15) Neural Networks: Neuron Model, Activation Functions, Network Architecture, Forward Propagation Slides, Math Notes  
(16-18) Loss Functions, Backpropagation, Gradient Descent, Initialization, Normalization, Vanishing/Exploding Gradients Slides, Math Notes  
(19) Neural Network Regularization (Dropout, Weight Decay), Optimization (SGD, Adam, RMSprop), Hyperparameter Tuning, Model Evaluation Slides, Math Notes CT 2
(20) Convolutional Neural Networks (CNNs): Convolution, Filters, Layers, Feature Maps, Pooling, Architecture Design Slides, Math Notes  
(21) CNNs: Forward Propagation, Loss Functions, Backpropagation, Popular Architectures (VGG, ResNet) Slides, Math Notes  
(22) CNNs with Attention Mechanisms (SE Block, CBAM Overview), Transfer Learning, Fine-Tuning, Model Visualization Slides, Math Notes  
(23) Cross-Validation, Bootstrap Slides, Math Notes  
(24) Ensemble Methods: Bagging, Boosting, Random Forests Slides, Math Notes  
(25) Generative Models: Autoencoders, VAE, GANs, Conditional/Modern Generative Models, Applications, Evaluation, Ethics, Course Wrap-Up Slides  
  Final Examination   Â