Network Science and Machine Learning

Network science and Machine Learning for next-generation communications networks (2020)

What you get

All nationalities are eligible to apply for this studentship. This 3-year studentship includes student fees and a tax-free stipend starting at £15,285 per annum. It also comes with a generous Research Training Support Grant.

Type of award

Postgraduate Research

PhD project

Profile Description

The management of communications networks involves a number of challenges: 1) high-dimensional data, 2) the underlying systems that generate the data are changing continuously, 3) the data generated by IT systems isredundant and extremely noisy. Because these three properties make the application of traditional machine learning and data science techniques very challenging, network operators are engaged in the development of ad-hoc techniques. The aim of this projectis to leverage a combination of network science and machine learning approaches to improve the capacity of networks management operators to efficiently and rapidly respond to failures. The three main axes of research will be: (a) the development of a dynamic functional connectivity inference framework specifically adapted to the constraints of IT network management providing a greater understanding of zones of influence for both hardware and software quantities; (b) network controllability via manipulationof the higher-order structure of the network using local information only; and (c) the development of novel mechanisms to identify and predict network incidents and service outages in the presence of change in large scale network deploymentsthat may involve elastic, distributed and migrate-able services, distributed network controllers and virtual network functions.

The research will take place under the umbrella of an active and well-funded collaboration between Prof Luc Berthouze (Complex Systems; AI research group) and Dr George Parisis (Computer Networks; FOSS group) within the Department of Informatics, at the University of Sussex, UK. Interested candidates will also have the opportunity to collaborate with academic and industry partners of the supervisors as well as others. Starting date is flexible.

Eligibility

Depending on the chosen topic, you will have a first-class honour degree or equivalent, or an MSc degree (preferably), in Computer Science, Mathematics or Physics (or relevant disciplines). You will have (and enjoy using) strong analytical skills as well as excellent programming skills in at least one of C++, Python, Matlab.

You will have a good knowledge of English and be able to express yourself clearly in both written and spoken form.You will have had a long-standing interest in pursuing doctoral studies, and be enthusiastic about delving into and contributing to the exciting and fast-moving research area that network science is. Ideally, you will have had some experience working across disciplines, perhaps, during a research internship, a final year project or an MSc dissertation.

You will have shown the ability to work both as part of a team and independently. Depending on the nature of your topic, you will have knowledge and experience in at least one of the following fields: graph theory, machine learning, probability theory / stochastic processes, big data analysis. Domains in which you will have applied this knowledge could include (but not be limited to): computer networks, neuroscience, epidemiology, analysis of social media.

Entry requirements: https://www.sussex.ac.uk/study/phd/apply

Deadline

1 September 2020 0:00

How to apply

Apply online for a full time PhD in Informatics using our step by step guide (http://www.sussex.ac.uk/study/phd/apply). Here you will also find details of our entry requirements.

Please clearly state on your application form that you are applying for a 'Network science and Machine Learning for next-generation communications networks'.

Please note that we request a ‘Statement of Research Interests'. Your statement (no more than 500 words) should answer two questions:(i) Why are you interested in the topic described above?(ii) What relevant experience do you have? In addition to this, we would also like you to submit a sample of your written work. This might be a chapter of your final year or masters dissertation or a published paper.

Contact us

Applicants interested in the post, seeking further information or feedback on their suitability are encouraged to contact Prof Luc Berthouze and Dr George Parisis. All applications must be made via the website mentioned above.

Timetable

Application Deadline:	Applications will stay open until the postion is filled.
Interview date:	Interviews will take place on a rolling basis.