Postgraduate Studies in Computer & Electronic Engineering

 

The MuST research group offers a postgraduate programme focussed on machine learning. To qualify, prospective students must have an undergraduate degree in a related Engineering field and 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.

 

Through its affiliation with the South African Centre for Artificial Intelligence Research (CAIR), 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 August-September.

 

Recent topics:

  • Deep learning theory
    • Generalisation in deep learning: Bilateral synergies in MLP learning (2021)
    • Exploring data utilisation in neural networks (2021)
    • Interpreting deep neural networks with sample sets  (2021) 
    • Parametric studies of translation invariance and distortion robustness in Convolutional Neural Networks (2020)
    • Contrasting Convolutional Neural Networks with alternative architectures for transformation invariance (2020)
    • Activation functions in deep neural networks (2019)
  • Space weather applications of DNNs
    • ​Deep neural networks for prediction of solar flares (2020)
    • Interpretability of deep neural networks for SYM-H prediction (2020)
  • Speech and language applications of DNNs
    • Robust speaker diarisation in telephone conversations (2021)
    • Automatic speech recognition on poor quality audio using Generative Adversarial Networks (2021)
    • Embedding recognised speech in a multilingual environment (2020)
    • Classifying recognised speech with deep neural networks (2020)
  • Other applications of DNNs
    • Machine learning in the presence of a mismatch between training and evaluation sets (2020)
    • Sailplane cross-country performance optimisation using deep neural network

Study leaders: 

Prof Marelie Davel, Prof Etienne Barnard & Dr Stefan Lotz

External domain experts participate as co-supervisors where relevant. Currently, the group includes the following experts:

Studies are also conducted in collaboration with other NWU faculty from the School of Electronic, Electrical and Computer Engineering, currently Prof Albert Helberg & Prof Alwyn Hoffman.