I am a Lecturer in Artificial Intelligence in the Department of Computer Science and a member of the Nature Inspired Computing and Engineering (NICE) Group. Prior to joining Surrey, I was a Postdoctoral Research Assistant in Machine Learning working with Steve Roberts in the Machine Learning Research Group, University of Oxford. I was also a Junior Research Fellow at the Wolfson College, University of Oxford. I completed my Ph.D. in electrical engineering with Mark Coates at McGill University in Montréal, Canada.
My research interests are in the areas of machine learning and statistical signal processing. I have a particular interest in designing Bayesian and Monte Carlo inference techniques effective in high-dimensional spaces. I have applied machine learning and signal processing techniques to diverse problem domains including environmental acoustic detection, device-free target tracking in sensor networks, and microwave breast cancer detection.
Areas of specialism
Bayesian inference; Monte Carlo sampling; Target tracking; Statistical machine learning
I am actively looking for PhD students with a strong interest and background in deep learning and Bayesian inference. Please contact me if you are interested in working with me.
Information about a range of PhD studentships is available at https://www.surrey.ac.uk/doctoral-college/prospective-postgraduate-researchers/fees-funding
In the media
I am interested in foundational machine learning topics motivated by applications aiming to improve human life and environment. I am currently working on improving the ability of deep neural networks to quantify uncertainty in their predictions, which can benefit vast data science domains, from disease diagnostics to autonomous driving. My work on Monte Carlo sampling and Bayesian classifier fusion has found applications in microwave breast cancer detection, device-free people tracking for smart home, and malaria-vectoring mosquito detection using low-cost mobile phones. My research is impact-driven and received media coverage from MIT Technology Review, Digital Trends, New Scientist, The Guardian, BBC, among other venues.
- COMM054: Data Science Principles and Practices (2019 - )
- COM1033: Foundations of Computing II (2018 - )
- Year 1 (undergraduate) Coordinator and Personal Tutor (2018 - )
- Industry Placement Visiting Tutor (2018 - )
- Departmental Seminar Organiser (2018 - 2019)
Postgraduate research supervision
PhD students (Principal Supervisor):
Xiongjie Chen (2019 - )
Hao Wen (2019 - )
network, NIPS 2018 workshop proceedings
quickly process large quantities of unstructured data to prevent and respond to natural disasters. Crowdsourcing provides an efficient mechanism to generate labels from unstructured data to prime machine learning algorithms for large scale data analysis. However, these labels are often imperfect with qualities varying among different citizen scientists, which prohibits their direct use with many state-of-theart machine learning techniques. We describe BCCNet, a framework that simultaneously aggregates biased and contradictory labels from the crowd and trains an
automatic classifier to process new data. Our case studies, mosquito sound detection for malaria prevention and damage detection for disaster response, show the efficacy of our method in the challenging context of developing world applications.
paper, we propose to combine the strengths of invertible particle flow and SMCMC by constructing a composite Metropolis-Hastings (MH) kernel within the SMCMC framework using invertible particle flow. In addition, we propose a Gaussian mixture model (GMM)-based particle flow algorithm to construct effective MH kernels for multi-modal distributions. Simulation results show that for high-dimensional state estimation example problems the proposed kernels significantly increase the acceptance rate with minimal additional computational overhead
and improve estimation accuracy compared with state-of-the-art filtering algorithms.