Course Code | 045101091 |
Course Title | Machine Learning: the Past, Current and Future |
Course Category | Specialty Basic Courses |
Course Nature | Compulsory Course |
Class Hours | 16 teaching sessions, including 0 lab sessions |
Credits | 1 |
Semester | The second semester |
Institute | School of Computer Science and Engineering |
Program Oriented | Computer Science and Technology Creative Full English Creative Class and Full English United Class |
Teaching Language | English |
Prerequisites | None |
Student Outcomes (Special Training Ability) | In addition the introduction of basic theory and tools of machine learning, we will also explore applications of machine learning techniques in real applications: information retrieval, business intelligent, pattern recognition and intelligent logistics. |
Course Objectives | This course aims to provide undergraduate students with basic knowledge about machine learning. We provide students with strong foundation to facilitate their future study and research in machine learning and pattern recognition. Classmates will explore the past, current and future of machine learning through group discussion and thesis writing. We hope that this course could inspire classmate’s interests to further explore and research in machine learning. |
Course Description | Machine learning is one of important branches of computer science. Every year, there are a large number of Ph.D. and master research students graduated with major in this area. Many research works have been done in both theoretical research and real world applications of machine learning techniques. One could find of machine learning techniques play important roles in automatic control, bioinformatics, information retrieval, pattern recognition, business intelligence, intelligent logistics, computer games, smart phones, etc. When we find that intelligent systems are gradually involved in our daily life in every aspect, a question arose: How to create these important and powerful intelligent systems? In this course, I will explore how to make computer intelligent together with classmates. |
Teaching Content and Class Hours Distribution | Introduction to Machine Learning (4 hours)
A brief on what are learning and machine learning. Introduction of some basic tools for machine learning Machine Learning Methods (4 hours)
A brief on several common machine learning methods Machine Learning Application-I (4 hours)
Example applications in business intelligence Machine Learning Application-II (4 hours)
Example applications in image retrieval and logistics
|
Experimental Teaching | No experiment |
Teaching Method | Traditional teaching, group discussion, reports, and assignments. |
Examination Method | Class participation: 50% Homeworks: 50% |
Teaching Materials and Reference Books | Textbook: No dedicated textbook. Students are encouraged to search related knowledge on the Internet or the following research oriented databases: Major References: IEEE Xplorer (http://ieeexplore.ieee.org/) Science Direct (http://www.sciencedirect.com) SpringerLink (http://www.springerlink.com/) |
Prepared by Whom and When | Wing Yin NG, 17 October 2019 |
