Introduction to Machine Learning

Course Code: B63008H

Course Name: Introduction to Machine Learning (B)

Credits: 2.0

Level: Undergraduate

Pre-requisite: Advanced algebra, Probability and Mathematical Statistics

Lecture Time: 10 weeks, 2 sessions/week, 2 hours/session

Instructors: Dr. Yanyan Lan

Course Description

This course is designed for undergraduate students who should master basic principle and method. The requirements are: (1) Have a basic understanding of ideas and methods of machine learning; (2) Master methods of supervised learning, unsupervised learning, and semi-supervised learning. (3) Have a basic understanding of machine learning theory.

Topics and Schedule

  1. Introduction of Machine Learning (2 hrs)

1.1.   History of machine learning and practical application

1.2.   Introduction of relevant mathematics knowledge

  1. Basic Method of Supervised Learning (20 hrs)

2.1.   Linear regression

2.2.   Lasso

2.3.   Decision tree

2.4.   Logistic regression

2.5.   Naïve Bayesian Model

2.6.   Maximum likelihood and maximum a posteriori

2.7.   Support Vector Machine

2.8.   Regularization and model selection

  1. Statistical Learning Theory (2 hrs)

3.1.   Sample complexity

3.2.   VC dimension

3.3.   Generalization bounded

  1. Probabilistic Graphical Model (4 hrs)

4.1.   EM method

4.2.   Gaussian Mixture

4.3.   Hidden Markov Model

  1. Method of Semi-supervised Learning and Unsupervised Learning (6 hrs)

5.1.   K-Means clustering

5.2.   Principal Component Analysis (PCA)

5.3.   Singular Value Decomposition (SVD)

5.4.   Fisher LDA

5.5.   Co-training

5.6.   Artificial Neural Networks


Students will be given a big project demonstration (2 hrs). Design algorithm or programming to solve practical problems according to the learned knowledge such as recommendation system, search engine, and etc.


M. Bishop (2006), Pattern Recognition and Machine Learning. Springer.

Trevor Hastie, Robert Tibshirani, and Jerome Friedman (2001). The Elements of Statistical Learning. Springer.

Kevin Patrick Murphy, Machine Learning: A Probabilistic Perspective, the MIT Press