Module Catalogues, Xi'an Jiaotong-Liverpool University   
 
Module Code: CSE315
Module Title: Machine Learning
Module Level: Level 3
Module Credits: 5.00
Academic Year: 2017/18
Semester: SEM1/SEM1
Originating Department: Computer Science and Software Engineering
Pre-requisites: N/A
   
Aims
To equip students with a broad expertise in the basic principles, techniques, algorithms, implementation and applications of Machine Learning.
Learning outcomes 
CODE OUTCOME

A Have a solid understanding of the theoretical issues related to problems that machine learning algorithms try to address.

B Be able to ascertain the properties of existing ML algorithms and new ones.

C Be able to apply ML algorithms for specific problems.

D Be proficient in identifying and customising aspects on ML algorithms to meet particular needs.

Method of teaching and learning 
Students will be expected to attend two hours of a formal lecture and two hours for either a tutorial or a lab section in a typical week. Lectures will introduce students to the academic content. Tutorials/labs will be used to expand the students understanding of lecture materials. In addition, students will be expected to devote unsupervised time to private study. Private study will provide time for reflection and consideration of lecture material and background reading. Two assessments will assess how well students keep up with the material presented in the lectures. A written examination at the end of the module will assess the academic achievement of students.
Syllabus 
1 week: Introduction, overview and history of machine learning.


4 weeks: Supervised learning: topics selected from regression, neural networks, decision trees, discriminant analysis, support vector machines, nearest neighbors, etc.


3 weeks: Unsupervised learning: topics selected from hierarchical clustering, k-Means clustering, Gaussian mixture models, Self-organizing maps, hidden Markov models, etc.


2 weeks: Reinforcement learning: Markov decision process, Q-Learning, etc.


2 weeks: Evolutionary learning: Genetic algorithm.


1 week: Revisions (Week 14)

Delivery Hours  
Lectures Seminars Tutorials Lab/Prcaticals Fieldwork / Placement Other(Private study) Total
Hours/Semester 26     13  13    98  150 

Assessment

Sequence Method % of Final Mark
1 Assessment Task 1 15.00
2 Assessment Task 2 15.00
3 Written Examination 70.00
1 Assessment Task 1 15.00
2 Assessment Task 2 15.00
3 Written Examination 70.00

Module Catalogue generated from SITS CUT-OFF: 10/22/2017 10:46:15 AM