This opportunity is now closed.

Funded PhD Opportunity

Active Bayesian machine learning

Subject: Computer Science and Informatics


Summary

Overview

The aim of this project is to develop state-of-the-art Bayesian machine learning methods for use in applications where we generate our own training data using computer simulation. The research will be carried out within the Artificial Intelligence Research Group at Ulster University, and methods tested using a high impact application from the physical sciences, under active development at the University of Manchester.

Background

Recent failures in deep learning, such as the first fatality from driverless cars, have highlighted the importance of reporting the uncertainty in predictions made by machine learning [1]. The need to consider predictive uncertainty is common, and applies as much to the learning of atomic properties [2] as it does to autonomous driving. Bayesian machine learning [3] naturally provides us with estimates of the uncertainty in our predictions. The behaviour of a Bayesian model is a balance between what the training data says, and our pre-existing belief of how the model should behave, as expressed through probability distributions called priors.

This project concerns Bayesian machine learning for applications where we can generate our own training data using computer simulations. Choosing which data to learn from is called active learning, and is particularly interesting for Bayesian models given that the accuracy of our model depends also on the choice of prior.

Proposed research

The methods developed will be generic, but tested using a state-of-the-art application from computational chemistry that has been developed and updated over the past decade at the University of Manchester [4,5]. The exact research challenges to be addressed in this project can be tailored to the interests and experience of the PhD candidate, but example problems include:

*Active learning for multi-fidelity models: The simulations that generate the training data have tolerance parameters that enable us to control its fidelity (accuracy). Should we generate small amounts of high-fidelity data to train our models from, or large amounts of low-fidelity data, or a combination of both? How does this affect the uncertainty in our predictions?

*Prior specification: How can we best construct informative priors for a new problem, using (i) data from related problems, and (ii) domain knowledge, such as physical laws that place constraints on the data? How much data will we need to generate to counterbalance prior misspecification? Other challenges exist in areas such as dimensionality reduction, multi-task learning, and Bayesian optimization. All of these problems are of course not mutually exclusive, but overlapping.

[1] Kendall, A. (2018) Deep learning is not good enough, we need Bayesian Deep Learning for safe AI: Available at: https://alexgkendall.com/computer_vision/bayesian_deep_learning_for_safe_ai/

[2] Peterson, A., et al. (2017) Addressing uncertainty in atomistic machine leaning, Physical Chemistry Chemical Physics 19 10978-10985.

[3] Murphy, K. (2012) Machine Learning: A Probabilistic Perspective, MIT Press.

[4] Handley, C. M., Hawe, G. I., Kell, D. B., Popelier, P. (2009) Optimal construction of a fast and accurate polarisable water potential based on multipole moments trained by machine learning, Physical Chemistry Chemical Physics 11 6365-6376.

[5] McDonagh, J., et al. (2018) Machine Learning of Dynamic Electron Correlation Energies from Topological Atoms, Journal of Chemical Theory and Computation, 14 (1)


Essential criteria

  • To hold, or expect to achieve by 15 August, an Upper Second Class Honours (2:1) Degree or equivalent from a UK institution (or overseas award deemed to be equivalent via UK NARIC) in a related or cognate field.

Funding

    The University offers the following awards to support PhD study and applications are invited from UK, EU and overseas for the following levels of support:

    Vice Chancellors Research Studentship (VCRS)

    Full award (full-time PhD fees + DfE level of maintenance grant + RTSG for 3 years).

    This scholarship will cover full-time PhD tuition fees and provide the recipient with £15,000 maintenance grant per annum for three years (subject to satisfactory academic performance). This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.

    Vice-Chancellor’s Research Bursary (VCRB)

    Part award (full-time PhD fees + 50% DfE level of maintenance grant + RTSG for 3 years).

    This scholarship will cover full-time PhD tuition fees and provide the recipient with £7,500 maintenance grant per annum for three years (subject to satisfactory academic performance). This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.

    Vice-Chancellor’s Research Fees Bursary (VCRFB)

    Fees only award (PhD fees + RTSG for 3 years).

    This scholarship will cover full-time PhD tuition fees for three years (subject to satisfactory academic performance). This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.

    Department for the Economy (DFE)

    The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £ 15,009 per annum for three years. EU applicants will only be eligible for the fee’s component of the studentship (no maintenance award is provided). For Non-EU nationals the candidate must be "settled" in the UK. This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.

    Due consideration should be given to financing your studies; for further information on cost of living etc. please refer to: www.ulster.ac.uk/doctoralcollege/postgraduate-research/fees-and-funding/financing-your-studies


Other information


The Doctoral College at Ulster University


Reviews

Profile picture of Adrian Johnston

As Senior Engineering Manager of Analytics at Seagate Technology I utilise the learning from my PhD ever day

Adrian Johnston - PhD in Informatics

Watch Video  

Key dates

Submission deadline
Monday 18 February 2019

Interview Date
25 to 29 March 2019


Applying

Apply Online  


Campus

Jordanstown campus

Jordanstown campus
The largest of Ulster's campuses


Contact supervisor

Dr Glenn Hawe


Other supervisors

Related Funded Opportunities

Context aware Brain Computer Interfaces and Internet of Things (IoT)

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

Autonomous Object Recognition for Robots

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics|Computer Science and Informatics

 View details

Neural Data Science, Computational Neuromodulation, and Metalearning

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics|Computer Science and Informatics

 View details

Augmented Reality Brain-computer Interface

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics|Computer Science and Informatics

 View details

Gaining a better understanding of our Planet through Deep Learning-based Data Analytics

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

Data Analytic Technologies to Combat Human Trafficking

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

Adaptive Learning for Modelling Non-stationary Dynamical Systems

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics|Computer Science and Informatics

 View details

Computational and Mathematical Modelling of Predator-Prey Systems

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

Applying Natural Language Processing to the automated fact checking of legal documents

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics|Computer Science and Informatics

 View details

Computing

Subject: Computer Science and Informatics

 View details

Deep-learning assisted tele-medicine for the delivery of diabetic retinopathy screening in low- and middle-income countries

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics|Computer Science and Informatics

 View details

The impact of the analytical performance of laboratory tests on clinical decision making

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics|Computer Science and Informatics

 View details

Intelligent Systems

Subject: Computer Science and Informatics

 View details

Sensing human emotion within pervasive environments

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

Magic Hands: Non-invasive hand tracking for virtual reality and game based stroke rehabilitation.

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics|Computer Science and Informatics

 View details

Intelligent Mobility Aids to Promote Physical Activity in Children with Cerebral Palsy

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics|Nursing and Health

 View details

Network Machine Learning Approach to Financial Crime Detection

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

Trusting the uncertainty in machine learning predictions

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

Mapping the Brain with Zero Knowledge using advanced AI and Data Analytics

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics|Computer Science and Informatics

 View details

Neuro Sense: serious games for in-situ autism assessment

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

Exploiting Brain Inspired Information Processing in Hardware to Develop Highly Reliable, Always-on Smart Sensor Systems.

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics|Computer Science and Informatics

 View details

Autonomous Decision Analytics by Integrating Machine Learning and Symbolic Reasoning

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

An Approach for Constructing and Sharing Open Data Sets in Experimental Pervasive Computing

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

RECASE: Robot-Enabled Care system in Smart Environments

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

Sensing and Modelling Air Quality for Healthy Living (SMAQ)

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

Chatbots for decision support and reporting in healthcare

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

PostCrypt: Data Security for the future

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

Enhanced Augmented Reality with Data Engineering and AI for Smart Digital Education

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics|Education

 View details

AI-enabled Automated Behaviour Analysis for User-centric Systems

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

Quantitatively assessment of limb motion utilising wearable sensors in remote rehabilitation

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details

Towards Trusted Cognitive Intelligence for User-centric Smart Systems

Closing date:
Friday 7 February 2020
Subject: Computer Science and Informatics

 View details