Postgraduate studies

text

Postgraduate Studies in Computer & Electronic Engineering

The MUST research group offers a postgraduate programme focused on machine learning. To qualify, prospective students must have a relevant undergraduate degree (e.g. BSc, BEng) and a solid background in mathematics. Additionally, prospective students should have an interest in machine learning, deep neural networks, statistical pattern recognition and/or generalisation within the context of Artificial Intelligence.

MUST students either study the essence of the learning process of different types of deep networks, or apply and improve these techniques in the context of a specific application domain. In practice, students work with MUST researchers on one of our research projects, using popular deep learning tools (such as Pytorch and Tensorflow) to explore specific questions on new and existing data sets. Our students learn about machine learning algorithms, development of software, and the design and interpretation of machine learning experiments. In addition to the generic skills, many of our students working on specific application domains gain the knowledge and skills required to effectively operate in these specialised domains.

Through its affiliations and collaborative activities with SANSA, CAIR and NITheCS, MUST is able to offer a number of M.Eng and PhD bursaries annually. We consider exceptional applications throughout the year (space allowing), and have an open application process in July to August.

MUST students enjoy considerable in-group support during their studies. Senior students are available to assist new students, resources are regularly shared on the group’s various communication channels, students meet with the entire group weekly and at least every second week with their supervisors in smaller groups. There's even a dedicated socials organiser to ensure an appropriate portion of fun and downtime.

Besides learning how to conduct research, postgraduate study at MUST is also a “finishing school” of sorts for engineers. Our students work in an informal office setting where they learn to balance the freedom to explore with a variety of responsibilities, such as contributing to group activities, participating in collaborative software development, sharing research results and guiding younger researchers when the time comes. Students leave MUST having learnt essential soft skills that will help them hit the ground running at their next opportunity, with a healthy understanding of work-life balance. Students at MUST also have the option of continuing their academic career, by applying to enrol for a PhD degree after completion of a master's degree.

Recent topics

Deep learning theory: Generalisation
- Exploring generalisation of convolutional neural networks using unit-level information (PhD, current)
- An empirical investigation of the capacity gap in feature-based knowledge distillation from deep ensembles (MSc, current)
- Exploring product units in the context of modern deep learning (MSc, current)
- Detecting problematic samples in deep learning (MEng, 2026)
- Inducing diversity among subpredictors in an implicit deep ensemble (MEng, 2026)
- Generalisation in deep convolutional neural networks (PhD, 2025)
- Margin-based regularization for deep neural networks (MEng, 2025)
- Exploring the effect of clustered hidden representations on generalisation in DNNs (MEng, 2025)
- On margin-based generalisation prediction in deep neural networks (PhD, 2024)
- Exploring data utilisation in neural networks (MEng, 2022)
- Generalisation in deep learning: Bilateral synergies in MLP learning (PhD, 2021)
- Machine learning in the presence of a mismatch between training and evaluation sets (MSc, 2021)
- Parametric studies of translation invariance and distortion robustness in Convolutional Neural Networks (MEng, 2020)
- Contrasting Convolutional Neural Networks with alternative architectures for transformation invariance (MEng, 2020)
- Activation functions in deep neural networks (MEng, 2019)
Deep learning theory: Interpretability
- Visualising feature effects for deep time series models (MEng, current)
- Evaluating feature attribution for multivariate time series (MEng, 2025)
- Interpreting deep neural networks with sample sets (MEng, 2022)
Space weather applications of DNNs
- Solar wind coupling functions with Kolmogorov-Arnold Networks (MSc , current)
- Knowledge discovery with additive attribution methods for geomagnetic index prediction (MEng, 2023)
- Deep neural networks for prediction of solar flares (MEng, 2020)
- Interpretability of deep neural networks for SYM-H prediction (MEng, 2020)
Speech and language applications of DNNs
- Evaluating the impact of preprocessing on sign language translation (MEng, 2026)
- Text Generation Language Model for Sepedi-English Mixed Text Using Transformer-Based Architecture (PhD, 2026)
- Whale call detection with deep neural networks (MEng, 2023)
- Domain adaptation for speaker diarisation in low-resource environments (MEng, 2021)
- Automatic speech recognition on poor quality audio using Generative Adversarial Networks (MEng, 2021)
- Embedding recognised speech in a multilingual environment (MSc, 2020)
- Classifying recognised speech with deep neural networks (MEng, 2020)
Other applications of DNNs
- Real-time cattle identification using deep vision models (PhD, current)
- Practical finger-angle estimation from sEMG using subject-specific DNN (MEng, current)
- Automated detection of structural changes in informal settlements (MSc, current)
- Adaptive channel estimation for next-generation cellular communication using deep learning (PhD, 2026)
- Development of a deep neural network framework for sailplane cross-country performance optimisation (PhD, 2024)
- Exploring tabular transformers for short-term insurance modelling (MEng, 2024)
- Traffic flow prediction with graph convolutional networks (MEng, 2022)
- Channel estimation and equalisation using generative adversarial networks (MEng, 2022)

Study leaders

Prof Marelie Davel, Prof Stefan Lotz, Prof Ben Opperman, Dr Tian Theunissen, Dr Randle Rabe, Dr Coenraad Mouton, Dr Aldrin Ngorima, Dr Obsa Gilo Wakuma.

Domain experts participate as co-supervisors where relevant. Currently, the group collaborates with the following experts:

Prof Albert Helberg, Electronic, Electrical and Computer Engineering, NWU & Telenet.
Prof Rojanette Coetzee, Industrial Engineering, NWU & Agri-Systems
Mr Ian Thomson, Electronic, Electrical and Computer Engineering, NWU & Beyond Limits
Prof Henri Marais, Electronic, Electrical and Computer Engineering, NWU, Agri-Systems
Prof Christo Venter, Faculty of Natural and Agricultural Sciences, NWU & Centre for Space Research.