MUST Deep Learning is a research group within the Faculty of Engineering at NWU. We perform basic and applied research in machine learning, with an emphasis on the theory and application of deep learning. Our theoretical work focuses on generalisation in deep learning, and the interpretability of deep learning models. Building on a strong track record in the application of machine learning to multilingual speech processing, our current application domains are diverse, ranging from speech processing to space weather prediction to industrial applications of deep learning.
The core MUST research group is small but collaborates widely, and is active in various local and international research projects, working with partners and clients from industry, government, and NGOs. We are also proud to be a node of the South African National Centre for Artificial Intelligence Research (CAIR). Researchers and students from MUST participate regularly in local and international workshops and conferences, such as AAAI, Interspeech, SLTU, ICASSP and SACAIR.
At MUST we provide a focused, project-oriented learning environment to younger researchers, and provide senior researchers with significant freedom in choosing how they contribute to the group’s activities. Our research activities include a student lab in Potchefstroom, linking with remote students (at different university campuses or in industry) as well as a satellite research office in Hermanus, where group members and visiting scientists can spend time in an environment that is conducive towards focused research.