Machine Learning
| Code | School | Level | Credits | Semesters |
| COMP3038 | Computer Science | 3 | 20 | Autumn Malaysia |
- Code
- COMP3038
- School
- Computer Science
- Level
- 3
- Credits
- 20
- Semesters
- Autumn Malaysia
Summary
Providing you with an introduction to machine learning, pattern recognition, and data mining techniques, this module will enable you to consider both systems which are able to develop their own rules from trial-and-error experience to solve problems, as well as systems that find patterns in data without any supervision. In the latter case, data mining techniques will make generation of new knowledge possible, including very big data sets. This is now fashionably termed 'big data' science. You'll cover a range of topics including: machine learning foundations; pattern recognition foundations; artificial neural networks; deep learning; applications of machine learning; data mining techniques and evaluating hypotheses.
Target Students
Available to Level 3 students in the School of Computer Science. Available to inter-campus mobility students and other exchange students in computer science. This module is not available to students not listed above, without explicit approval from the module convenor(s). Prior knowledge of high-level computer programming skills (e.g. Matlab and Python) and mathematical skills (e.g. linear algebra, differentiation, probability) is required. This module is part of the Artificial Intelligence, Modelling and Optimisation theme in the School of Computer Science.
Classes
- Two 2-hour lectures each week for 12 weeks
- One 2-hour computing each week for 12 weeks
Activities may take place every teaching week of the Semester or only in specified weeks. It is usually specified above if an activity only takes place in some weeks of a Semester Further Activity Details: Method and Frequency of Class and timing of class: two two-hour lectures per week, with practical problems being tackled in group coursework assignments. One two-hour lab session will be held, in which groups of students work on their coursework assignments or engage in further practice led learning.
Assessment
- 30% Coursework 1: Group programming assignment including a series of lab reports
- 70% Exam 1 (2-hour): 2 hour written examination
Educational Aims
To introduce the principles, techniques and applications of machine learning and pattern recognition.To enable students the to appreciate some of the most widely used machine learning and pattern recognition algorithms and applications, as well as data mining techniques and their applications.To enable the students to understand and be able to put into practice a variety of machine learning and pattern recognition algorithms, as well as data mining techniques.To enable students to apply data mining techniques on real data sets, some of which can be described as big data sets.To allow students to appreciate the potential and limitation of big dataLearning Outcomes
Knowledge and Understanding:
Understanding the capabilities, strengths and limitations of machine learning paradigms(A3)
An appreciation of learning systems and learning algorithms (A4)
Intellectual Skills:The ability to understand complex ideas and relate them to specific situations (B4)
The ability to identify both capabilities and limitations of a machine learning or pattern recognition method (B4)
Professional SkillsThe ability to implement selected machine learning operations including learning algorithms and apply them in real world applications (C1)
The ability to evaluate available machine learning models and learning algorithms and select those appropriate to a given task (C3)
Transferable Skills:The ability to address real problems and assess the value of their proposed solutions (D1)
The ability to retrieve and analyse information from a variety of sources and produced detailed written reports on the result (D4)
Conveners
- Dr Zhiyuan Chen