Navgation: HOME > Graduate study > Content
《Machine Learning》Course Syllabus
Time:2017-04-11 Hit:

《Machine Learning》Course Syllabus

Course Name

Machine Learning

Instructor

Dr. Cheng Lu

Course Type

Research Direction Course

Prerequisite Courses

Linear Algebra, Statistics

Discipline

Computer Science

Learning Method

Mentoring, discussion and programing

Semester

1st semester

Hours

40

Credit

2

 

1. Objective & Requirement

Machine learning is the science of getting computers to learning from historical data without human’s interactions. In the past decade, machine learning has brought us speech recognition, self-driving cars, effective web search, and to name a few. Machine learning has been successfully applied in our daily life that you probably use it dozens of times a day without knowing its present. In this course, you will learn manyup-to-date machine learning techniques, and gain access the implementation and getting them to work for your concrete applications.

This course provides a broad introduction to machine learning, data-mining, and statistical pattern recognition. The objective of this course is to establish fundamental concepts on machine learning. The course will be teaching in full English, all graduate students, including thesis-based and PhD students whose discipline are related to computer science are welcome to select this course. The prerequisite courses are linear algebra and statistics.

2. Primary coverage

We will cover the following core topics plus a set of selected topics:

(i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks).

(ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning).

(iii) Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI).

(iv) Numerous case studies and applications to learn how to apply learning algorithms to build smart robots (perception, control), text understanding (web search, anti-spam), computer vision, medical informatics, audio, database mining, and other areas.

3. Textbook

Tom Mitchell, Machine Learning. McGraw-Hill, 1997.

4. Reference Books

  1. Richard Duda, Peter Hart and David Stork, Pattern Classification, 2nd ed. John Wiley & Sons, 2001.

  2. Richard Sutton and Andrew Barto, Reinforcement Learning: An introduction. MIT Press, 1998.

  3. Trevor Hastie, Robert Tibshirani and Jerome Friedman, The Elements of Statistical Learning. Springer, 2009.

5. Course Evaluation (Tentative)

Assignments                           30%

Course Project                        40%

Midterm Exam (in-class)          30%