I am seeking applications for two EPSRC DTP Ph.D Studentships that are
available in the Department of Mathematics, at Brunel University London, to
work with me, in the area of Bayesian learning. There is a possibility of
offering the studentships to international and EU-based applicants, in
addition to consideration of UK-based students. Please contact me at
This email address is being protected from spambots. You need JavaScript enabled to view it., if interested. The brief project outlines are
as below:
Sufficiently Deep Supervised Learning in High-Dimensions & Fast Prediction,
with Applications
-----------------
This project is dedicated to the application of a recently-advanced,
dual-layered and free-form Bayesian supervised learning strategy that will be
employed to learn the high-dimensional functional relationship between system
parameters and a high-dimensional observed variable that affects said
parameters. To reduce prediction times, while acknowledging complexities of
real data, we will develop a classifier of the system parameter vector, given
associated observable values, subsequent to the rigorous learning of the
inter-variable relationship.
Bayesian Prediction, Notwithstanding Unattainable Learning Given Unavailable
Training Data
-------------
This project addresses the need to predict values of a system-variable, at
which a related observable is realised, even when learning the functional
relationship between the system-variable and observable is impossible, owing
to unavailability of training data, and ignorance about the probabilistic
nature of relevant variables. We will employ a new Bayesian method to achieve
such prediction in a dynamical system, by learning the function that drives
evolution of the observable, and its probability distribution.
Logistics:
-------------
The Ph.D projects are set to start on the 1st of October 2020. Successful
applicants will receive an annual stipend (bursary) of £17,285 plus payment of
their full-time home, EU or international tuition fees for a period of 36 or
48 months (3 or 4 years).
Applicants will have or be expected to receive a first or upper-second class
honours degree in an Engineering, Computer Science, Design, Mathematics,
Physics or a similar discipline. A Postgraduate Masters degree is not required
but may be an advantage. Experience in MCMC techniques, will be an advantage
for these projects. The applicant should be highly motivated, and have good
communication skills.
To apply, please submit your application documents (see list below) by Noon on
Friday 12 June 2020 to This email address is being protected from spambots. You need JavaScript enabled to view it. Interviews will take
place in July 2020.
* Your up-to-date CV;
* Your personal statement (300 to 500 words) summarising your background,
skills and experience;
* Your Undergraduate/Postgraduate Masters degree certificate(s) and
transcript(s);
Thank you very much.
Best,
Dalia
