Deep learning is a family of machine learning techniques (originally inspired by the idea of artificial neural networks) that nowadays consist of large, complex, layered models that excel at solving ‘human-like’ tasks. It is one of the core technologies driving current innovations in Artificial Intelligence. MUST is a technology-focused group: by growing skills and expertise within a narrow techno
logy focus, it produces researchers that solve complex tasks across a variety of domains. Applications are developed with domain partners from industry and government. Current application domains include speech and language modelling, space weather modelling, and industrial applications of deep learning (for example, airfoil design, telecommunications, and intelligent transport systems). The MUST research group slots into larger collaborative initiatives such as the Centre for Artificial Intelligence Research (CAIR) and the current NITheCS, coordinating a research programme in each. It forms the CAIR Deep Learning node and coordinates the ‘Machine learning in support of theoretical and computational sciences’ research programme in NITheCS. MUST regularly participate in national and international conferences, including prestigious conferences such as the Association for the Advancement of Artificial Intelligence (AAAI) Conference on Artificial Intelligence, and the International Joint Conference on Artificial Intelligence (IJCAI). The group has a distributed model: research activities include student labs in Potchefstroom, linking with remote students nationally, as well as a satellite research office in the Western Cape.
