Statistical Machine Learning
| Code | School | Level | Credits | Semesters |
| MATH4069 | Mathematical Sciences | 4 | 20 | Full Year UK |
- Code
- MATH4069
- School
- Mathematical Sciences
- Level
- 4
- Credits
- 20
- Semesters
- Full Year UK
Summary
Statistical machine Learning is a topic at the interface between statistics and computer science that concerns models that can adapt to and make predictions based on data. This module builds on principles of statistical inference and linear regression developed in MATH2011 and MATH4065 / MATH4019 to introduce a variety of methods of clustering, dimension reduction, regression and classification. Much of the focus is on the bias-variance trade-off, and on methods to measure and compensate for overfitting. The learning approach is hands-on, with students using R extensively in studying contemporary statistical machine learning methods, and in applying them to tackle challenging real-world applications.
Target Students
MMaths students and suitably qualified MSc students.
Classes
- One 3-hour lecture each week for 20 weeks
Assessment
- 32% Project 1: Group written report (Autumn)
- 8% Presentation 1: Group oral presentation (Autumn)
- 48% Project 2: Group written report (Spring)
- 12% Presentation 2: Group oral presentation (Spring)
Assessed by end of spring semester
Educational Aims
Thiscourse provides students with skills that employers typically seek in graduates who enter the workplace, including general skills such as problem solving, proficient oral and written communications and teamwork; and the specific technical skills needed to develop and apply machine learning approaches for challenging real world applications.Learning Outcomes
A student who completes this course will be able to:
L1 - state and apply standard results relating to methods of supervised learning;
L2 - explain the suitability and limitations of various machine learning methods in given applications;
L3 - use statistical software packages to apply methods to data sets, make predictions and assess predictive accuracy;
L4 - evaluate and implement a strategy for approaching machine learning problems that are open ended and of non-routine nature;
L5 - synthesise and present a systematic account of machine learning concepts applied to given problems, communicating results using appropriate style and terminology.