UET
Since 2004
ĐẠI HỌC CÔNG NGHỆ, ĐHQGHN
VNU-University of Engineering and Technology
INT3405E - Machine Learning
Lecture 0: Course Introduction
Hanoi, 01/2025
Course Introduction
● Course Name/Code: Machine Learning / INT3405
● #Credits: 03
● Lecture Organization: 2+1 ~ 2-hour lecture + 1-hour Jupyter Notebook
● Course Plan: 15 weeks ~ 11 lessons + 1 midterm + 3 project presentations
● Learning outcomes:
○ Understand basic concepts of machine learning
○ Understand machine learning techniques and algorithms
○ Can use tools/libraries to implement machine learning models
○ Can apply machine learning models in revealing new knowledge
○ Can apply the obtained knowledge to solve real world problems
FIT-CS INT3405E - Machine Learning 2
Teaching Team
Instructors: Tạ Việt Cường, Phd,
Le Bang Giang, MsC
About myself:
Backgrounds: Computer Science
Years in ML: Since 2009
Research Direction: Machine Learning Theory and Applications,
Reinforcement Learning, Deep Graph Learning.
FIT-CS INT3405E - Machine Learning 3
Course Materials
● Primary Textbook:
○ Học máy thống Kê, Trần Quốc Long, Tạ Việt Cường, NXBĐHQGHN 2025.
○ Kevin P. Murphy (2022). Probabilistic Machine Learning: An Introduction. MIT Press
○ Trevor Hastie , Robert Tibshirani , Jerome Friedman (2001). The Elements of Statistical
Learning, Springer
● Reference Textbook:
○ Christopher M. Bishop (2006). Pattern Recognition and Machine Learning, Springer
○ Ian Goodfellow and Yoshua Bengio and Aaron Courville (2016). Deep Learning, MIT Press
○ Athem Alpaydin (2010). Introduction to Machine Learning, The MIT Press.
FIT-CS INT3405E - Machine Learning 4
Basic Knowledge and Prerequisites
● Mathematics Foundations:
○ Linear Algebra: Understanding vectors, matrices, matrix operations
○ Calculus: derivatives, integrals, and partial derivatives
○ Probability & Statistics
○ Optimization
● Programming Skills:
○ Python
○ Data Structures and Algorithms
○ Software Engineering
FIT-CS INT3405E - Machine Learning 5
Course Outline
● Week 1: Introduction
● Week 2: General Concepts
● Week 3: Linear Regression
● Week 4: Classification (1) - Logistic Regression, Bayes
● Week 5: Classification (2) - Decision Tree, KNN
● Week 6: Classification (3) - SVM & Variants
● Week 7: Feature Selection & Model Optimization
● Week 8: Unsupervised Learning
● Week 9: Mid-term Exam
● Week 10: Deep learning (1) - Perceptron, MLP
● Lecture 11: Deep learning (2) - CNN, RNN
● Lecture 12: Introduction to MLOps
● Lecture 13: Reinforcement Learning
● Lecture 14-15: Project Presentation
FIT-CS INT3405E - Machine Learning 6
Course Assessment
● Class Attendance: 10% (3rd week onwards)
● Mid-term Exam: 30%
○ 10 MCQs + 2-3 practical questions
● Final Project: 60%
○ Group project: A team of 3 students
○ Goal:
■ Choose a problem of a given list, i.e., datasets
■ Implement ML algorithms
■ Evaluate and improve the algorithms
■ Presentation report
FIT-CS INT3405 - Machine Learning 7
UET
Since 2004
ĐẠI HỌC CÔNG NGHỆ, ĐHQGHN
VNU-University of Engineering and Technology
Q&A