Machine Learning & Applied Statistics Course
Imperial College Business Summer School
Key Information
Campus location
London, United Kingdom
Languages
English
Study format
On-Campus
Duration
3 weeks
Pace
Full time
Tuition fees
GBP 2,115 *
Application deadline
Request info
Earliest start date
Request info
* early bird fee one session; £3,807 - two sessions; £2,350 - regular fee one session; £4,230 - two sessions
Scholarships
Explore scholarship opportunities to help fund your studies
Introduction
Gain data analytics skills and apply them to challenging problems in finance and bioimaging
Machine Learning & Applied Statistics Summer School will introduce you to a range of quantitative methods from mathematics, statistics and computing and will enable you to use these methods in applications in various fields including finance and bioimaging.
This course is offered jointly by the Department of Mathematics and Imperial College Business School and facilitated by the Quantitative Sciences Research Institute. You will be taught by faculty from the Department of Mathematics.
Teaching methods
Teaching will take place on campus, in our multi-mode enabled lecture theatres.
The course will be taught in line with government COVID-19 guidance and restrictions for teaching. This may include social distancing and reduced capacity in lecture theatres. Should government guidelines in place at the time limit or prevent on-campus teaching, we reserve the right to deliver some or all of the course fully online.
Assessment
- One individual examination after the first week – (33.33% of final mark)
- One individual final examination at the end of the third week – (66.66% of final mark)
Imperial College London will issue an official transcript with a final overall numerical mark – a breakdown of results will not be provided.
Imperial College London reserves the right to change or alter the courses offered without notice.
Program Outcome
By the end of this machine learning summer course, you will:
- Understand a range of statistical and mathematical techniques to manipulate empirical data sets
- Implement machine learning algorithms
- Explain time series modelling
- Understand spatial data modelling
- Apply learnt techniques to real-life data sets
Curriculum
Week one
In the first week, students will learn basic programming skills and they will be introduced to key ideas from machine learning, such as linear and nonlinear methods, how to deal with the problem of overfitting. They will also explore the concepts of supervised and unsupervised learning as well as the basic ideas behind deep learning.
Week two
In the second week, students will learn basic probability theory and will then study the key ideas of time series analysis including how to deal with trend and seasonality in data and how to forecast in linear time series models. The theoretical developments will be applied to various data sets with a particular focus on financial data. Students will also learn how risk measures such as value-at-risk and expected shortfall can be computed.
Week three
In the third week, students will familiarise themselves with handling spatial data. The quantitative methods taught in this part of the course are motivated by applications in the life sciences, more precisely from bioimaging. Bioimaging methods aim to observe biological processes at the cellular and sub-cellular levels. It is a fundamental tool of the life sciences and has led to some of the most important advances in modern medicine. Students will explore some statistical methods that can be used for analysing and interpreting spatial data extracted from bioimages.