Big Data and High-Performance Computing
Taught by experts in statistics, operational research and computer science, this programme will help you develop both the theoretical understanding and practical experience of applying methods drawn from data science and analytics.
Big Data and High-Performance Computing is a multidisciplinary Summer School split across the Schools of Computer Science and Informatics, Mathematics and Physics and Astronomy. Working together, these Schools will introduce you to a range of in-demand skills for extracting and handling ‘big data’, discovering and communicating meaningful patterns from the data, and applying modelling tools to help businesses and government organisations make better decisions.
This Summer School will begin with introductory lectures, workshops and practical sessions intended to provide a basic understanding of programming languages (Python, R and C) and elementary statistical data analysis methods. These activities will provide a grounding for subsequent more advanced topics in data analysis and computing later in the School. The focus will be on practical applications of the various techniques described, showcases by examples from the world-leading research carried out in the School of Physics and Astronomy on data obtained from astronomical satellites such as Planck and Herschel as well as gravitational wave research.
The high-performance computing component of the Summer School will look at important distinctions between shared and distributed memory models, and between data and task-based parallelism, and teach you how to write simple parallel applications. The focus will mainly be on the practical issues of programming modern parallel computers using OpenMP, MPI, and CUDA.
To make sure you benefit from this Summer School, we suggest that applicants are familiar with the C programming language, R and Python. However, if you are unfamiliar with these languages, but still wish to participate in the course, we can also provide you with tutorial material in advance of the summer school. Although it would be beneficial, no advanced expertise in programming or in statistics is required.
If you have any queries about this Summer School, the academic content or how you can prepare for this course, please get in touch with Sophie Lewis on PSE-ISS@cardiff.ac.uk.
Please note this itinerary is not final and is subject to change.
|Saturday 20 July 2019||Arrival in Cardiff (pick up from Heathrow provided)|
|Sunday 22 July 2019||Social event|
|Monday 22 July 2019||Welcome lecture and orientation scavenger hunt|
|Tuesday 23 July 2019||Lecture: Crash course in Python and introduction to data analysis|
Practical session: Python
Problem-solving informal assessment
|Wednesday 24 July 2019|
Lecture: Introductory Data Analysis (formatting, processing)
Practical Session: Gravitational Waves
Key-note lecture on Gravitational waves
Tour: Astronomical Instrumentation (detectors)
|Thursday 25 July 2019|
Lecture: Multivariate regression models
|Friday 26 July 2019|
Lecture: Data mining, classification and clustering
|Saturday 27 July 2019||Field trips and free time|
|Sunday 28 July 2019||Field trips and free time|
|Monday 29 July 2019|
Lecture: Machine learning and deep learning
|Tuesday 30 July 2019|
Lecture: Examples of parallelism; shared and distributed memory architectures
Lecture: Programming with OpenMP 4.0
|Wednesday 31 July 2019|
Lecture: Introduction to message passing and the MPI programming model
|Thursday 1 August 2019|
Lecture: Programming with GPUs
|Friday 2 August 2019|
Final Gala Ceremony
|Saturday 3 August 2018||Departure from Cardiff (drop off to Heathrow provided)|
The fee for the Summer School is £1,995.
This includes tuition fees, accommodation, 10 meals per week (breakfast and lunch, Monday to Friday), airport pick up and drop off from Heathrow airport on fixed dates (pick up is on 20 July, drop off is 3 August) and excursions organised by Cardiff University (such as Stonehenge and industrial visits).
If you have any questions or for more information, please email email@example.com.