- University of Oxford (2021-2025): DPhil Engineering Science
- University of Oxford (2017-2021): MEng Engineering Science (First class)
Graph Rewiring Project, Networks & Society Group, MLRG, Oxford University (Aug 2022 - Present)
- Continuation of AIMS mini-project supervised by Francesco Di Giovanni, Michael Bronstein and Xiaowen Dong.
- Developing a GNN message-passing framework that allows for adaptive information flow using dynamic rewiring and delayed propagation
Zero Shot Coordination Project, Foerster Lab for AI Research, Oxford University (Apr 2022 – Aug 2022)
- AIMS mini-project investigating zero-shot coordination for continuous state-action spaces.
- Experimentation with (multi-agent) reinforcement learning algorithms in accelerated physics engine, using Jax/Flax.
HumBug Project, Machine Learning Research Group, Oxford University (Jun 2020 – Sep 2021)
- Summer research placements supervised by Prof. Stephen Roberts.
- Project concerns the use of low-cost smartphones and audio data analysis for the identification and tracking of mosquito species, for malaria prevention.
- Working on codebase and obtaining experimental results for Bayesian NN species classification for HumBugDB paper, accepted at NeurIPS 2021.
- Worked on testing neural network mosquito classifier, and building/testing voice activity detector for removal of human speech from recordings (2020).
Final Year Undergraduate Project, Bayesian Exploration Lab, Oxford University (Sep 2020 – June 2021)
- MEng Masters project supervised by Prof. Michael Osborne (project report pdf available here).
- Investigating the use of single-sample gradient estimators of evidence lower bound for variational inference, working with Edward Wagstaff.
Intern, QinetiQ (Jul-Sep 2018, Jun-Sep 2019)
- Awarded student scholarship; undertook two summer internships in RF, Secure Networks and Comms
- Worked with team developing Counter-UAV Radar system, completed projects in MATLAB including data analysis on Doppler signatures and calibration files of a phased array radar, and used Monte Carlo simulation to find optimal calibrations.
ML Project Leader, Engineers Without Borders Oxford (Sep 2020 – Jun 2021)
- Led a team of ten in conducting a COVID-19 medical image deep learning project.
- Also served as Director of Partnerships (Aug 2019 – Jul 2020).
STEP UP Ambassador, *New College Oxford Access & Outreach Dept. (Nov 2017 – Jun 2020)
- Ambassador to visiting state schools, leading tours and assisting with annotation of admissions tests.
- Python: experienced across a range of personal and academic projects, with data science (NumPy, SciPy, Pandas, etc.) and deep learning libraries (PyTorch, Jax/Flax).
- MATLAB: experience working with during QinetiQ internships and for and undergraduate projects.
- Grade 8 Jazz Clarinet with Distinction, Trinity College London (2016).
HumBugDB: A Large-scale Acoustic Mosquito Dataset (2021)
Accepted at the 35th Conference on Neural Information Processing Systems (NeurIPS 2021) Track on Datasets and Benchmarks.
Kiskin, I., Sinka, M., Cobb, A.D., Rafique, W., Wang, L., Zilli, D., Gutteridge, B., Dam, R., Marinos, T., Li, Y. and Msaky, D., 2021. HumBugDB: A Large-scale Acoustic Mosquito Dataset. arXiv preprint arXiv:2110.07607.
HumBug–An Acoustic Mosquito Monitoring Tool for use on budget smartphones (2020)
Published in Methods in Ecology and Evolution, 12(10), pp.1848-1859.
Sinka, M.E., Zilli, D., Li, Y., Kiskin, I., Kirkham, D., Rafique, W., Wang, L., Chan, H., Gutteridge, B., Herreros‐Moya, E. and Portwood, H., 2021. HumBug–An Acoustic Mosquito Monitoring Tool for use on budget smartphones. Methods in Ecology and Evolution, 12(10), pp.1848-1859.