I am an associate professor of Applied Mathematics in the Faculty of Science at Stellenbosch University, South Africa. My research is primarily focused around applied machine learning. I have worked in the domains of probabilistic robotics and computer vision for many years, and have some recent experience also in computational linguistics, reinforcement learning and deep generative modelling. I like working on applications for nature conservation, social impact and public health, and I am passionate about building and serving machine learning communities all across Africa.

I completed an MSc in Applied Mathematics at Stellenbosch in 2005, and a PhD in Computer Science at Sheffield Hallam University in the UK in 2008. After a short postdoc at South Africa's Council for Scientific and Industrial Research, I returned to Stellenbosch in 2009 where I have been developing and teaching a variety of undergrad and postgrad courses in Applied Mathematics and Computer Science, and working with many inspiring grad students.

Office:  Room A3043, General Engineering Building, Banghoek Road        Email:  wbrink [at] sun [dot] ac [dot] za        Phone:  +27 (0)21 808 4218

Deep Learning Indaba
The Deep Learning Indaba is an organisation whose mission is to strengthen machine learning and artificial intelligence in Africa. We work towards the goal of Africans being not only observers and receivers of ongoing advances, but active shapers and owners of these technologies. Visit our website to find out more!

Google DeepMind Scholarships
I coordinate the Google DeepMind scholarship programme at Stellenbosch University, and am proud to represent the first African university on this programme. There is not an open call for applications at the moment, but do keep an eye out for possible future opportunities. More information here.

Maties Machine Learning
Herman Kamper and I created MML in 2018, in an effort to bring together researchers and students from across departments and faculties of Stellenbosch University. It is primarily a seminar series and discussion forum, and anyone at the university interested in machine learning is most welcome to join us.

Courses I am teaching in 2026:

•   •   Probability Theory and Statistics 114

•   •   Probabilistic Modelling and Reasoning 812

•   •   Computer Vision 842

Other courses I've taught in the past:

•   •   Modelling in Mechanics 144

•   •   Applied Differential Equations 244

•   •   Numerical Methods 262

•   •   Numerical Analysis 324

•   •   Applied Fourier Analysis 364

•   •   Computer Vision 364

•   •   Computer Vision 792

•   •   Digital Image Processing 793

•   •   Mathematics for Machine Learning 811

I am the programme director of a great one-year structured MSc in Machine Learning and Artificial Intelligence at Stellenbosch University. Follow the link for more information!

I am also a visiting lecturer in the AI for Science Masters programme at the African Institute for Mathematical Sciences.

•   •   Fred de Villiers (PhD, co-supervising with Benjamin Rosman)

•   •   Katerine Sadie (PhD, co-supervising with Johan du Preez)

•   •   Faith Neema Benson (PhD, co-supervising with Amina Abubakar)

•   •   Evander Nyoni (PhD)

•   •   Daniel Rajaonarivonivelomanantsoa (PhD, co-supervising with Arnu Pretorius)

1. Back-translation and unsupervised domain adaptation for machine translation of Arabic dialects [link]
   A. Salim, W. Brink
   ACM Transactions on Asian and Low-Resource Language Information Processing, 2026

2. Entropy estimation in cluster graphs [preprint]
   K. Sadie, J. du Preez, W. Brink
   Preprints, 2026052092, 2026

3. Key predictors of postpartum depression and anxiety symptoms among mothers in Kilifi, Kenya [link]
   F. Benson, R. Odhiambo, W. Brink, A. Ngugi, A. Waljee, E. Weinheimer-Haus, C. Moyer, J. Zhu, A. Abubakar
   Frontiers in Psychiatry: Public Mental Health, 17:1790893, 2026

4. On the reliability of likelihoods from conditional flow matching generative models trained in feature space [link]
   S. Josias, W. Brink
   IET Computer Vision, 20(1):e70061, 2026

5. Predicting off-track development in infants aged 0–6 months in low-resource settings using machine learning [link]
   F. Benson, R. Odhiambo, A. Ngugi, W. Brink, A. Waljee, C. Moyer, J. Zhu, F. Agoi, A. Abubakar
   Pediatric Research, 2026

6. An empirical study of task and feature correlations in the reuse of pre-trained models [link] [arXiv]
   J. Mohamud, W. Brink
   NeurIPS Workshop on Unifying Representations in Neural Models (UniReps), PMLR vol. 322, pp. 374-384, 2026

7. Written on the wings: morphometrics, mortality and more [link]
   J. Hargrove, P. Landi, W. Brink
   South African Journal of Science, vol. 121, no. 11/12, art. 22461, 2025

8. Application of machine learning in early childhood development research: a scoping review [link]
   F. Benson, D. Chelangat, W. Brink, P. Mwangala, A. Waljee, C. Moyer, A. Abubakar
   BMJ Open, 15:e100358, 2025

9. Risk model for predicting gaps in surgical oncology care among patients with stage I-III rectal cancer [link]
   Y. Moodley, W. Brink, J. van Wyk, S. Kader, S. Wexner, A. Neugut, R. Kiran
   JCO Global Oncology, 11:e2400480, 2025

10. Multimodal base distributions in conditional flow matching generative models [link]
    S. Josias, W. Brink
    British Machine Vision Conference (BMVC), paper 492, 2024

11. Reliability of AI vs manual digitization of anatomical landmarks [link]
    J. Dujardin, P. Solano, J. Hargrove, E. Nazif, W. Brink, P. Landi, D. Geldenhuys
    European Society for Vector Ecology Conference, 2024

12. Multimodal base distributions for continuous-time normalising flows [pdf]
    S. Josias, W. Brink
    NeurIPS Workshop on the Symbiosis of Deep Learning and Differential Equations (DLDE), 2023

13. Improving machine translation of Arabic dialects using unsupervised domain adaptation
    A. Salim, W. Brink
    Women in Machine Learning Workshop at NeurIPS, 2023

14. Deep learning approaches to landmark detection in tsetse wing images [link] [data]
    D. Geldenhuys, S. Josias, W. Brink, M. Makhubele, C. Hui, P. Landi, J. Bingham, J. Hargrove, M. Hazelbag
    PLOS Computational Biology, 19(6):e1011194, 2023

15. Scaling multi-agent reinforcement learning to full 11 vs 11 simulated robotic football [link]
    A. Smit, H. Engelbrecht, W. Brink, Arnu Pretorius
    Autonomous Agents and Multi-Agent Systems, vol. 37(1), art. 20, 2023

16. Learning to pay multiple attention with fully convolutional transformers [pdf]
    S. Mensah, B. Bah, W. Brink
    Southern African Conference for Artificial Intelligence Research (SACAIR), pp. 67-77, 2022

17. Jacobian norm regularisation and conditioning in neural ODEs [link] [pdf]
    S. Josias, W. Brink
    Artificial Intelligence Research, CCIS vol. 1734, pp. 31-45, 2022

18. Improving the performance of image captioning models trained on small datasets [link] [pdf]
    M. du Plessis, W. Brink
    Artificial Intelligence Research, CCIS vol. 1551, pp. 77-91, 2022

19. Machine learning models for stomatal conductance in multiple tree species across different forest biomes [link]
    A. Saunders, D. Drew, W. Brink
    Trees, Forests and People, vol. 6, art. 100139, 2021

20. Mava: a research framework for distributed multi-agent reinforcement learning [arXiv]
    A. Pretorius, K. Tessera, A. Smit, C. Formanek, S. Grimbly, K. Eloff, S. Danisa, L. Francis, J. Shock, H. Kamper, W. Brink, H. Engelbrecht, A. Laterre, K. Beguir
    arXiv preprint, arXiv:2107.01460, 2021

21. Class-selective mini-batching and multitask learning for visual relationship recognition [link]
    S. Josias, W. Brink
    SAIEE Africa Research Journal, vol. 112, no. 2, pp. 99-109, 2021

22. BINet: a binary inpainting network for deep patch-based image compression [link] [arXiv]
    A. Nortje, W. Brink, H. Engelbrecht, H. Kamper
    Signal Processing: Image Communication, vol. 92, art. 116119, 2021

23. Towards the localisation of lesions in diabetic retinopathy [link] [arXiv]
    S. Mensah, B. Bah, W. Brink
    Lecture Notes in Networks and Systems: Intelligent Computing, vol. 285, pp. 100-107, 2021

24. Link prediction in knowledge graphs using latent feature modelling and neural tensor factorisation [pdf]
    L. Magangane, W. Brink
    Southern African Conference for Artificial Intelligence Research (SACAIR), pp. 335-348, 2020

25. Image identification of Protea species with attributes and subgenus scaling [link] [pdf]
    P. Thompson, W. Brink
    IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 2094-2102, 2020

26. Learning fine-grained control for mapless navigation [pdf]
    F. de Villiers, W. Brink
    SAUPEC/RobMech/PRASA Conference, pp. 666-671, 2020

27. Batch construction and multitask learning in visual relationship recognition [pdf]
    S. Josias, W. Brink
    SAUPEC/RobMech/PRASA Conference, pp. 713-718, 2020

28. Towards automating healthcare question answering in a noisy multilingual low-resource setting [link]
    J. Daniel, W. Brink, R. Eloff, C. Copley
    Meeting of the Association for Computational Linguistics (ACL), pp. 948-953, 2019

29. Analysis, prediction and comparison algorithms for water quality variables
    R. Elmahdi, W. Brink, J. Wilms
    Black in AI Workshop at NeurIPS, 2018

30. Short-term stream flow forecasting at Australian river sites using data-driven regression techniques [pdf]
    M. Steyn, J. Wilms, W. Brink, F. Smit
    International Work-Conference on Time Series (ITISE), pp. 865-876, 2017

31. A method for 3D stem analysis and its application on the occurrence of resin pockets in Pinus patula [link]
    F. Lerm, M. Blumentritt, W. Brink, B. Wessels
    European Journal of Forest Research, vol. 136, no. 3, pp. 411-420, 2017

32. A probabilistic graphical model approach to the structure-and-motion problem [arXiv] [pdf]
    S. Streicher, W. Brink, J. du Preez
    PRASA-RobMech International Conference, paper 8, 2016

33. Text detection in natural images with convolutional neural networks and synthetic training data [pdf]
    M. Grond, W. Brink, B. Herbst
    PRASA-RobMech International Conference, paper 20, 2016

34. The application of support vector regression for stream flow prediction on the Amazon basin [pdf]
    M. du Toit, J. Wilms, F. Smit, W. Brink
    Conference of the South African Society for Atmospheric Sciences, pp. 25-28, 2016

35. Pose uncertainty in occupancy grids through Monte Carlo integration [link]
    D. Joubert, W. Brink, B. Herbst
    Journal of Intelligent & Robotic Systems, vol. 77, no. 1, pp. 5-16, 2015

36. Long-term tracking of multiple interacting pedestrians using a single camera [pdf]
    M. Keaikitse, W. Brink, N. Govender
    PRASA, RobMech and AfLaT International Joint Symposium, pp. 59-65, 2014

37. Pose uncertainty in occupancy grids through Monte Carlo integration [pdf]
    D. Joubert, W. Brink, B. Herbst
    International Conference on Advanced Robotics (ICAR), paper 90, 2013

38. FastSLAM with stereo vision [pdf]
    W. Brink, W. Brink, C. van Daalen
    Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), pp. 24-30, 2012

39. Probabilistic outlier removal for robust landmark identification in stereo vision based SLAM [pdf]
    W. Brink, W. Brink, C. van Daalen
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2822-2827, 2012

40. Scene reconstruction from uncontrolled motion using a low cost 3D sensor [pdf]
    P. Joubert, W. Brink
    Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), pp. 13-18, 2011

41. Stereo vision as a sensor for EKF SLAM [pdf]
    W. Brink, W. Brink, C. van Daalen
    Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), pp. 19-24, 2011

42. A mesh-based approach to incremental range image integration [pdf]
    D. Joubert, W. Brink
    Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), pp. 74-79, 2011

43. Graph cut segmentation of range images into planar regions [pdf]
    S. Muller, W. Brink
    Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), pp. 108-113, 2011

44. Gain scheduling control of monocular vision-based human-following robot [pdf]
    M. Burke, W. Brink
    World Congress of the International Federation of Automatic Control (IFAC), pp. 8177-8182, 2011

45. Dense stereo correspondence for uncalibrated images in multiple view reconstruction [pdf]
    W. Brink, D. Joubert, F. Singels
    Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), pp. 39-44, 2010

46. Estimating target orientation with a single camera for use in a human-following robot [pdf]
    M. Burke, W. Brink
    Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), pp. 51-56, 2010

47. Multi-view 3D position estimation of sports players [pdf]
    R. Vos, W. Brink
    Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), pp. 299-304, 2010

48. Applying Bayesian segmentation in volumetric silhouette-based reconstruction [pdf]
    W. Brink
    Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), pp. 17-22, 2009

49. Real-time stereo reconstruction through hierarchical DP and LULU filtering [pdf]
    F. Singels, W. Brink
    Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), pp. 41-46, 2009

50. Combining motion detection and hierarchical particle filter tracking in a multi-player sports environment [pdf]
    R. Vos, W. Brink
    Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), pp. 65-70, 2009

51. Real-time 3D head tracking with an AAM-based particle filter [poster]
    W. Brink, M. Hoffmann
    International Computer Vision Summer School, 2009

52. Real-time surface tracking with uncoded structured light [pdf]
    W. Brink
    Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), pp. 91-95, 2008

53. Indexing uncoded stripe patterns in structured light systems by maximum spanning trees [pdf]
    W. Brink, A. Robinson, M. Rodrigues
    British Machine Vision Conference (BMVC), pp. 575-584, 2008

54. Willmore energy vs area as criteria for mesh optimisation [pdf]
    W. Brink, L. Alboul
    Numerical Geometry, Grid Generation and High Performance Computing, pp. 6-12, 2006

55. Mesh optimisation based on Willmore energy [pdf]
    L. Alboul, W. Brink, M. Rodrigues
    European Workshop on Computational Geometry, pp. 133-136, 2006

• Shane Josias (PhD 2024): Reliable likelihoods from continuous-time normalising flows [link]

• Samuel Ofosu Mensah (PhD 2023): Analysing retinal fundus images with deep learning [link]

• Dries Smit (PhD 2022): Multi-agent RL for 11-aside simulated robot soccer [link]

• Belinda Matebese (PhD 2019): Path planning using optimal control [link]

• Pieter Holtzhausen (PhD 2015): Video surveillance incorporating PTZ cameras [link]

• Aya Salim (MSc 2024): Neural machine translation for Arabic dialects [link]

• Cameron Painting (MSc 2024): Synthetic data generation for scene-text recognition

• Mikkel du Plessis (MSc 2022): Low-resource image captioning [link]

• Christiaan Louw (MSc 2022): Semi-supervised learning in computer vision [link]

• Wian Crous (MSc 2022): The class imbalance problem in computer vision [link]

• Evander Nyoni (MSc 2021): Neural machine translation for Southern African languages [link]

• Mulanga Makhubele (MSc 2021): FCNs for landmark detection in tsetse wing images [link]

• Luyolo Magangane (MSc 2020): Link prediction in knowledge graphs [link]

• Gregory Newman (MSc 2020): Video classification using deep learning [link]

• Reem Elmahdi (MSc 2020): Predicting water quality variables [link]

• Shane Josias (MSc 2020): Visual relationship recognition [link]

• Jeanne Daniel (MSc 2020): NLP for low-resource languages in healthcare [link]

• Peter Thompson (MSc 2020): Image identification of Protea species [link]

• Simbarashe Nyatsanga (MSc 2020): Automatic video captioning [link]

• Jaco Briers (MSc 2019): River flow routing using deep learning [link]

• Russell Kingwill (MSc 2019): Forecasting South African basic fuel prices [link]

• Jacques Marais (MSc 2018): Elephant detection in aerial images [link]

• Melise Steyn (MSc 2018): Stream flow forecasting using machine learning [link]

• Marco Grond (MSc 2017): Text detection in natural images [link]

• Simon Streicher (MSc 2016): Structure-from-motion with PGMs [link]

• Gideon Zuurmond (MSc 2015): Camera calibration through moiré pattern analysis [link]

• Alwyn Burger (MEng 2015): Occupancy grid mapping using stereo vision [link]

• Lloyd Hughes (MSc 2014): Mobile camera pose estimation [link]

• Pierre Joubert (MSc 2014): People detection and tracking in RGB and IR [link]

• Mogomotsi Keaikitse (MSc 2014): Long-term tracking of multiple pedestrians [link]

• Simon Muller (MSc 2013): Planar segmentation of range images [link]

• Wikus Brink (MEng 2012): Stereo vision for SLAM [link]

• Daniek Joubert (MSc 2012): Occupancy grid mapping with pose uncertainty [link]

• Michael Burke (MEng 2011): Visual control for a human-following robot [link]

• Robbie Vos (MSc 2010): Multi-view tracking of sports players [link]

• François Singels (MSc 2010): Real-time stereo reconstruction [link]