Machine Learning


The goal of the programme is to strengthen machine learning (ML) collaboration in NITheCS in two ways:

  • ML research: development of new, specialised machine learning techniques.
  • ML as a tool: applying machine learning for scientific modelling applications.
Machine learning research

Collaborating Researchers:

PI – Principal investigator (programme manager) 


Knowledge Discovery in Time Series Data
Machine learning techniques play an increasing role in assisting scientists and engineers in knowledge discovery: obtaining novel information from large, possibly complex data sets. Many practically important tasks, such as weather prediction, financial forecasting, or speech processing, are modelled using time series information. Knowledge discovery in time series data is an active field of research, with techniques such as feature attribution used to gain new insights into the underlying processes being modelled.

Machine Learning Forum
The programme aims to grow a forum for cross-cutting projects executed in other NITheCS focus areas, where those projects rely on machine learning expertise.


The programme is open to all NITheCS Associates who currently work in machine learning, or are interested in ML approaches in their research.

Events – 2023

NITheCS ML @ SACAIR: A one-day workshop will be hosted at the SACAIR 2023 conference on 5 December 2023. For more information, visit the conference website:

Link to ML workshop at SACAIR 2023

Marelie Davel (programme PI) showcased this research programme at the Deep Learning Indaba in Accra, Ghana through a poster presentation.

Stefan Lotz (programme PI) presented a talk on “Interpretable Machine Learning for Time Series Data” (view slides) at the second Workshop on Machine Learning, Data Mining and Data Assimilation in Geospace (LMAG 2023), 21 – 25 August 2023, Johns Hopkins University Applied Physics Laboratory, Maryland, USA.

Events – 2022

NITheCS ML @ SACAIR: A research programme year-end workshop was hosted at the SACAIR 2022 conference on 6 December 2022. Titled “Knowledge Discovery in Time Series Data”, the workshop brought together interested researchers in this field to share their recent findings and views. For more information, visit the conference website.

Stefan Lotz hosted a NITheCS colloquium on 19 September 2022.
Abstract  |  Video  |  Slides

The first workshop of the NITheCS Machine Learning programme took place virtually on 10 March 2022. The PIs introduced the project and its two streams, and participants shared their current ML-related work.


Interpretability of deep learning models
Jacques P. Beukes, Stefan Lotz and Marelie H. Davel, “Pairwise networks for feature ranking of a geomagnetic storm model”, South African Computer Journal, Vol 32, no2, pp35-55, December 2020.

Coenraad Mouton and Marelie H. Davel, “Exploring layerwise decision making in DNNs”, Artificial Intelligence Research (SACAIR 2021), Communications in Computer and Information Science, Vol 1551, pp 140-155, January 2022.

Marelie H. Davel, Stefan Lotz, Marthinus W. Theunissen, Almaro de Villiers, Chara Grant, Randle Rabe, Stefan Schoombie and Cleo Conacher, “Knowledge Discovery in Time Series Data“, Deep Learning Indaba Conference, Ghana, September 2023

Modelling time series data
Walter Heymans, Marelie H. Davel and Charl van Heerden, “Efficient acoustic feature transformation in mismatched environments using a Guided-GAN“, Speech Communication, Vol 143, pp 10-20, September 2022.

Marko Oosthuizen, Alwyn Hoffman and Marelie H. Davel, “A comparative study of graph neural network speed prediction during periods of congestion”, in Proc. 14th Int. Conf. on Neural Computation Theory and Applications (NCTA 2022), pp 331-338, October 2022

Thipe Modipa and Marelie H. Davel, “Two Sepedi‑English code‑switched speech corpora“, Language Resources and Evaluation, Vol 56, no 3, pp 703-727, September 2022..

Edrich Fourie, Jaco Versfeld, and Marelie H. Davel. “Neural speech processing for whale call detection”, Artificial Intelligence Research (SACAIR2022), Communications in Computer and Information Science, Vol 1734, pp 276-290, December 2022.

Walter Heymans, Marelie H Davel, and Charl van Heerden. “Multi-style training for South African call centre audio“, Artificial Intelligence Research, Communications in Computer and Information Science, Vol 1551, pp 111–124, September 2022.

Kimara Naicker, Ilya Sinayskiy, and Francesco Petruccione. “Machine learning for excitation energy transfer dynamics“, Physical Review Research, Vol 4, no 3: 033175, September 2022.

Kimara Naicker, Ilya Sinayskiy, and Francesco Petruccione. “Statistical and machine learning models for prediction of long-time excitation energy transfer dynamics“. arXiv preprint, 2022.

Other applications of machine learning
Andrew Oosthuizen, Marelie H. Davel and Albert Helberg, “Multi-Layer Perceptron for Channel State Information Estimation: Design Considerations “, in Proc. Southern Africa Telecommunication Networks and Applications Conference (SATNAC 2022), pp 94-99, August 2022.

Marthinus W. Theunissen, Coenraad Mouton and Marelie H. Davel, “The Missing Margin: How Sample Corruption Affects Distance to the Boundary in ANNs”, Artificial Intelligence Research (SACAIR2022), Communications in Computer and Information Science, Vol 1734, pp 78-92, Dec 2022.

Andrew J. Oosthuizen, Albert S.J. Helberg and Marelie H. Davel, “Adversarial Training for Channel State Information Estimation in LTE Multi-Antenna Systems”. Artificial Intelligence Research (SACAIR2022), Communications in Computer and Information Science, Vol 1734, pp 3-17.