Course Name: Machine Learning

Course Code:S2293210

Semester: 4

Credit: 2

Program: Computer science

Course Module: Optional

Responsible: Bo Wang

E-mail:2944440@qq.com

Department:Tianjin International Engineering Institute

Time Allocation(1 credit hour = 45 minutes)

Course Description

The course is optional designed for Engineering Mater of Computer Science in TIEI. This course is aimed at introducing the current mainstream theory of machine learning , methods, algorithms and applications, including the general machine learning, supervised learning, unsupervised learning, statistical learning, computational learning, Bayesian learning and the study of data compression. It also explains in detail a variety of learning theory, model, algorithm and application. This course emphasizes the combine of theory and application, so as to enhance their professional skills.

Prerequisite

• Probability and Mathematical Statistics: master the mathematical foundation of machine learning.

• Artificial Intelligence: understand the field of artificial intelligence, machine learning is the core of artificial intelligence.

Course Objectives

This course discusses the concept of machine learning to help students understand the field of artificial intelligence better and enhance their professional skills. After this course, students should be able to:

• Comprehensively master and understand machine learning research, the present situation and development of its application field, and to

• Master the mainstream learning methods and models, choose and implement the corresponding algorithm according to the practical problems.

CourseSyllabus

• Decision tree learning: master the basic knowledge of decision theory and information theory.

• Supervised learning and unsupervised learning: the concept of supervised learning and unsupervised learning.

• Evaluating hypotheses: common distribution and the method of maximum likelihood estimation.

• Linear regression model: the basic methods of linear regression.

• SVM: the basic principle of support vector machine.

• Graph model: from modelling to the implementation of algorithm.

• Expectation Maximization algorithm: the basic theory of EM algorithm and the use of EM algorithm.

• Hidden Markov Model and conditional random field model: a few classic algorithms of Hidden Markov Model.

Textbooks & References

• Christopher M. Bishop.Pattern Recognition and Machine Learning. Springer, 2007.

• Tom M. Mitchell.Machine Learning. McGraw-Hill Science/Engineering/Math, 1997.

• Kevin P. Murphy.Machine Learning. The MIT Press, 2012.

Capability Tasks

CT1: To understand basic science, and to have analytical ability and the ability to integrate related knowledge.

CT2: To be able to use related professional knowledge in the field of science and technology, to and understand primary concepts.

CT3: To master scientific method and the skills in applications of machine learning technologies, to be able to handle practical issues with machine learning methods.

CS1: To master the basic theory of machine learning, and to know its development status and trends.

CS2: To master the core knowledge of the machine learning and relevant engineering technology roundly, to have the preliminary ability of system development with the core knowledge and engineering technology.

Achievements

• To be familiar with the basic knowledge of decision tree and information theory. - Level: A

• To be familiar with the common distribution. - Level: A

• To master the way of linear regression, and to learn how to use regression software package in R, and how to solve practical problems. - Level: M

• To have a full understanding of classification problem, and to master some commonly classification methods. - Level: M

• To master the basic principle of SVM, and to learn to use SVM-to solve specific problems in their respective fields. - Level: M

• To master the process from modelling to algorithm implementation. - Level: M

• To master the basic theory of the EM-algorithm, and to learn how to use the EM-algorithm. - Level: M

• To master classic algorithms of hidden Markov model, and to learn to use hidden Markov model and conditional random field model to solve specific problems. - Level: M

Students: Computer science,Year 2