Dr Michael Smith

MScs, PhD

School of Computer Science

Lecturer

Outreach Lead

Member of the Machine Learning research group

Mike Smith
Profile picture of Mike Smith
m.t.smith@sheffield.ac.uk
Regent Court (DCS)

Full contact details

Dr Michael Smith
School of Computer Science
Regent Court (DCS)
211 Portobello
Sheffield
S1 4DP
Profile

Dr Michael Smith studied Computer Science at Warwick university, then, after a few years outside academia, joined Edinburgh to take MScs in Informatics and Neuroinformatics and a PhD in computational neuroscience, looking at where self-motion cues are processed and integrating, in the human brain (using fMRI).

After a bit of travelling he went to Kampala (Uganda) to lecture (in 2014) teaching AI to students at Makerere.

He is now a Research Fellow at the University of Sheffield in the department of Computer Science in the Machine Learning group. His work encompasses Differential Privacy and its applications to Gaussian process (GP) regression and classification, bounds on attacks to GP classifiers by adversarial examples, a kernel for regression over integrals and a method for tracking bees using retroreflective tags.

His work is in particular now focused on modelling air pollution in Kampala, using data from a network of low-cost sensors.

He is currently investigating probabilistically handling the calibration of the sensors using mobile units. This system will soon be incorporated into a pipeline providing live predictions for policy makers and stakeholders in the city.

Research interests
  • Gaussian Processes
  • Air pollution
  • Differential Privacy
  • Machine Learning for International Development
  • Bumblebee tracking
  • Adversarial Examples/bounds using Gaussian Processes
Publications

Journal articles

  • Yao M, Smith M & Peng C (2025) . Urban Forestry & Urban Greening, 105.
  • Chapman KE, Smith MT, Gaston KJ & Hempel de Ibarra N (2024) . Biology Letters, 20(4).
  • Smith MT, Ross M, Ssematimba J, lvarez MA, Bainomugisha E & Wilkinson R (2023) . Journal of the Royal Statistical Society Series C: Applied Statistics, 72(5), 1187-1209.
  • Smith MT, Grosse K, Backes M & lvarez MA (2023) . Machine Learning, 112(3), 971-1009.
  • Smith MT, Livingstone M & Comont R (2021) . Methods in Ecology and Evolution, 12(11), 2184-2195.
  • Smith MT, Alvarez MA & Lawrence ND (2021) Differentially private regression and classification with sparse Gaussian processes. Journal of Machine Learning Research, 22.
  • Fotheringham J, Smith MT, Froissart M, Kronenberg F, Stenvinkel P, Floege J, Eckardt K-U & Wheeler DC (2020) . BMC Nephrology, 21(1).
  • Smith MT, Zwiessele M & Lawrence ND (2016) Differentially Private Gaussian Processes.. CoRR, abs/1606.00720.
  • Bett D, Stevenson CH, Shires KL, Smith MT, Martin SJ, Dudchenko PA & Wood ER (2013) . The Journal of Neuroscience, 33(16), 6928-6943.
  • Feldwisch-Drentrup H, Barrett AB, Smith MT & van Rossum MCW (2012) . Journal of Neuroscience Methods, 210(1), 15-21.
  • Wutte M () . Frontiers in Psychology, 2.

Conference proceedings

  • McDonald TM, Ross M, Smith MT & lvarez MA (2023) Nonparametric gaussian process covariances via multidimensional convolutions. Proceedings of Machine Learning Research, Vol. 206 (pp 8279-8293). Palau de Congressos, Valencia, Spain, 25 April 2023 - 25 April 2023.
  • Gahungu P, Lanyon CW, lvarez MA, Bainomugisha E, Smith MT & Wilkinson RD (2022) Adjoint-aided inference of Gaussian process driven differential equations. Advances in Neural Information Processing Systems (NeurIPS 2022), Vol. 35. New Orleans, LA, USA, 28 November 2022 - 28 November 2022.
  • Grosse K, Smith MT & Backes M (2021) . 2020 25th International Conference on Pattern Recognition (ICPR) Proceedings (pp 4696-4703). MIlan, Italy, 10 January 2021 - 10 January 2021.
  • Yousefi F, Smith MT & Alvarez MA (2019) Multi-task Learning for aggregated data using Gaussian processes. Advances in Neural Information Processing Systems 32 (NeurIPS 2019), Vol. 32 (pp 15050-15060). Vancouver, Canada, 8 December 2019 - 8 December 2019.
  • Yousefi F, Smith MT & Alvarez Lopez M (2019) Multi-task Learning for aggregated data using Gaussian processes. Proceedings of the conference on Advances in Neural Information Processing Systems (NIPS 2019), Vol. 32. Vancouver, Canada, 8 December 2019 - 8 December 2019.
  • Smith MT, Alvarez MA, Zwiessele M & Lawrence ND () Differentially private regression with Gaussian processes. Proceedings of the 21st International Conference on Artificial Intelligence and Statistics(84) (pp 1195-1203). Lanzarote, Canary Islands, 9 April 2018 - 9 April 2018.

Preprints

  • Ross M, Smith MT & lvarez MA (2021) , arXiv.
  • Smith M (2019) .
  • Smith MT, Alvarez MA & Lawrence ND (2019) , arXiv.
  • Yousefi F, Smith MT & lvarez MA (2019) , arXiv.
  • Smith MT, Alvarez MA & Lawrence ND (2018) , arXiv.
Grants
  • BLE Bee Tracking System, Eva Crane Trust, 05/2025 - 05/2027, 瞿19,902, as Co-I
  • Pollinator: Using Data Driven Artificial Intelligence to Reveal Pesticide Induced Changes in Pollinator Behaviour, BBSRC, 02/2024 - 10/2025, 瞿321,811, as PI
  • AirQo, Industrial, 08/2019 - 07/2023, 瞿197,726, as PI
  • Improved Retroreflector Based Tracking for Bees, Eva Crane Trust, 03/2021 - 03/2023, 瞿13,909, as PI
  • Foraging distances and nest locations of bumblebees Bombus, Eva Crane Trust, 04/2019 - 12/2020, 瞿5,341, as PI

Links

Machine Learning research group