Lecturer(s): Professor Chenlei Leng
Prerequisite(s): ST221 Linear Statistical Modelling.
Commitment: 2 lectures and 1 computer laboratory per week. This module runs in Term 1.
Availability: Note that there is a cap on student numbers for this module. Pre-registration is essential and will open at 12 noon on 15th May 2019 for the 2019/20 academic year. Prioritisation will be given to students from Statistics department and those who have taken ST221, see the pre-registration page for details of the prioritisation rules and current status of allocations.
Content: In the modern world it is very easy to generate very large amounts of data. Capturing and exploiting the important information contained within such datasets poses a number of statistical challenges. It may not even be clear how much useful information the data contains. The module will cover a variety of algorithms developed to tackle some of these challenges.
Aims: To introduce students to algorithms suitable to the analysis of large datasets.
Objectives: At the end of the module, students should be able to implement various algorithms in the context of image analysis, handwriting recognition, personalized product suggestion, spam filtering and fraud detection.
Assessment: 50% coursework (three assignments) and 50% exam.
Deadline: Assignment 1: week 5, Assignment 2: week 8, Assignment 3: week 11.
Feedback: Marked assignments will be returned within 2 weeks.
Examination period: Summer