People
Latest Research Publications:
Statistics) degrees at Stellenbosch University. He joined the
Stellenbosch University Computer Science department in 2008. His PhD
thesis considered aspects of statistical learning theory, and his
subsequent research has focused on machine learning and decision
making under uncertainty.
He is a member of the Centre for Artificial Intelligence
Research, the Institute of Electrical and Electronics Engineers, the
International Computer Games Association, the South African
Statistical Association, and the South African Institute for Computer
Scientists and Information Technologists.
Latest Research Publications:
Denoising autoencoders (DAEs) have proven useful for unsupervised representation learning, but a thorough theoretical understanding is still lacking of how the input noise influences learning. Here we develop theory for how noise influences learning in DAEs. By focusing on linear DAEs, we are able to derive analytic expressions that exactly describe their learning dynamics. We verify our theoretical predictions with simulations as well as experiments on MNIST and CIFAR-10. The theory illustrates how, when tuned correctly, noise allows DAEs to ignore low variance directions in the inputs while learning to reconstruct them. Furthermore, in a comparison of the learning dynamics of DAEs to standard regularised autoencoders, we show that noise has a similar regularisation effect to weight decay, but with faster training dynamics. We also show that our theoretical predictions approximate learning dynamics on real-world data and qualitatively match observed dynamics in nonlinear DAEs.
@{202, author = {Arnu Pretorius, Steve Kroon, H. Kamper}, title = {Learning Dynamics of Linear Denoising Autoencoders}, abstract = {Denoising autoencoders (DAEs) have proven useful for unsupervised representation learning, but a thorough theoretical understanding is still lacking of how the input noise influences learning. Here we develop theory for how noise influences learning in DAEs. By focusing on linear DAEs, we are able to derive analytic expressions that exactly describe their learning dynamics. We verify our theoretical predictions with simulations as well as experiments on MNIST and CIFAR-10. The theory illustrates how, when tuned correctly, noise allows DAEs to ignore low variance directions in the inputs while learning to reconstruct them. Furthermore, in a comparison of the learning dynamics of DAEs to standard regularised autoencoders, we show that noise has a similar regularisation effect to weight decay, but with faster training dynamics. We also show that our theoretical predictions approximate learning dynamics on real-world data and qualitatively match observed dynamics in nonlinear DAEs.}, year = {2018}, journal = {35th International Conference on Machine Learning}, pages = {4141-4150}, month = {10/07-15/07}, publisher = {Proceedings of Machine Learning Research (PMLR)}, address = {Sweden}, isbn = {1938-7228}, }
No Abstract
@article{152, author = {Steve Kroon, A. Heavens, Y. Fantaye, E. Sellentin, H. Eggers, Z. Hosenie, A. Mootoovaloo}, title = {No evidence for extensions to the standard cosmological model}, abstract = {No Abstract}, year = {2017}, journal = {Physical Review Letters}, volume = {119}, pages = {101301-101305}, issue = {2017}, publisher = {American Physical Society}, url = {https://journals.aps.org/prl/abstract/10.1103/PhysRevLett.119.101301}, }
Reinforcement Learning (RL) is a powerful technique to develop intelligent agents in the field of Artificial Intelligence (AI). This paper proposes a new RL algorithm called the Temporal-Difference value iteration algorithm with state-value functions and presents applications of this algorithm to the decision-making problems challenged in the RoboCup Small Size League (SSL) domain. Six scenarios were defined to develop shooting skills for an SSL soccer robot in various situations using the proposed algorithm. Furthermore, an Artificial Neural Network (ANN) model, namely Multi-Layer Perceptron (MLP) was used as a function approximator in each application. The experimental results showed that the proposed RL algorithm had effectively trained the RL agent to acquire good shooting skills. The RL agent showed good performance under specified experimental conditions.
@article{151, author = {Steve Kroon, M. Yoon, J. Bekker}, title = {New reinforcement learning algorithm for robot soccer}, abstract = {Reinforcement Learning (RL) is a powerful technique to develop intelligent agents in the field of Artificial Intelligence (AI). This paper proposes a new RL algorithm called the Temporal-Difference value iteration algorithm with state-value functions and presents applications of this algorithm to the decision-making problems challenged in the RoboCup Small Size League (SSL) domain. Six scenarios were defined to develop shooting skills for an SSL soccer robot in various situations using the proposed algorithm. Furthermore, an Artificial Neural Network (ANN) model, namely Multi-Layer Perceptron (MLP) was used as a function approximator in each application. The experimental results showed that the proposed RL algorithm had effectively trained the RL agent to acquire good shooting skills. The RL agent showed good performance under specified experimental conditions.}, year = {2017}, journal = {Orion}, volume = {33}, pages = {1-20}, issue = {1}, publisher = {Operations Research Society of South Africa (ORSSA)}, address = {South Africa}, isbn = {2224-0004 (online)}, url = {http://orion.journals.ac.za/pub/article/view/542}, }
No Abstract
@{143, author = {Steve Kroon, PB Le Roux, Willem Bester}, title = {DSaaS: A cloud Service for Persistent Data Structures}, abstract = {No Abstract}, year = {2016}, journal = {CLOSER, 6th International Conference on Cloud Computing and Services Science}, pages = {37-48}, month = {23/04-25/04}, address = {Portugal}, isbn = {978-989-758-182-3}, }
No Abstract
@{129, author = {Steve Kroon, S. Nienaber, M.J. Booysen}, title = {A Comparison of Low-Cost Monocular Vision Techniques for Pothole Distance Estimation}, abstract = {No Abstract}, year = {2015}, journal = {IEEE Symposium Series on Computational Intelligence: IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems}, pages = {419-426}, month = {08/12-10/12}, }
Latest Research Publications:
Latest Research Publications:
Latest Research Publications:
Complex societal problems require a multi-disciplinary and multi-method approach to develop models that can support the development of solutions. General morphological analysis is a qualitative method to extract information from experts through facilitation and the use of customized software. Ontologies provide semantic representation of knowledge bases together with automated reasoning capabilities. These two approaches, combined with the use of concept maps, provide an integrated approach which can be used to understand complex and ill-structured problem domains and to aid in business modelling, strategy and scenario development and finally, decision-making. The resulting models are subjective constructs reflecting the knowledge and understanding of the analysts. Subsequent synthesis of new understanding and decisions rely on the robust validation and verification of the underlying logic and assumptions of the conceptual models.
Morphological Analysis and ontological constructs are applied in terms of an integrated Morphological Ontology Design Engineering methodology (MODE), which is based on Design Science. The paper is developed around the opportunity of scoping the applied research competence required to support a nation’s progress toward energy sufficiency. This paper presents a complex fused model for national energy sufficiency in New Zealand. The approach can be used to address other ill- structured complex societal problems.
@{375, author = {JH Roodt, Louise Leenen, Jansen van Vuuren}, title = {Modelling Of The Complex Societal Problem Of Establishing A National Energy Sufficiency Competence}, abstract = {Complex societal problems require a multi-disciplinary and multi-method approach to develop models that can support the development of solutions. General morphological analysis is a qualitative method to extract information from experts through facilitation and the use of customized software. Ontologies provide semantic representation of knowledge bases together with automated reasoning capabilities. These two approaches, combined with the use of concept maps, provide an integrated approach which can be used to understand complex and ill-structured problem domains and to aid in business modelling, strategy and scenario development and finally, decision-making. The resulting models are subjective constructs reflecting the knowledge and understanding of the analysts. Subsequent synthesis of new understanding and decisions rely on the robust validation and verification of the underlying logic and assumptions of the conceptual models. Morphological Analysis and ontological constructs are applied in terms of an integrated Morphological Ontology Design Engineering methodology (MODE), which is based on Design Science. The paper is developed around the opportunity of scoping the applied research competence required to support a nation’s progress toward energy sufficiency. This paper presents a complex fused model for national energy sufficiency in New Zealand. The approach can be used to address other ill- structured complex societal problems.}, year = {2020}, journal = {23rd International Conference on Information Fusion}, pages = {880 - 887}, month = {06/07-09/07}, isbn = {978-0-578-64709-8}, }
The protection and management of data, and especially personal information, is becoming an issue of critical importance in both the business environment and in general society. Various institutions have justifiable reasons to gather the personal information of individuals but they are required to comply with any legislation involving the processing of such data. Organisations thus face legal and other repercussions should personal information be breached or treated negligently. Most countries have adopted privacy and data protection laws or are in the process of enacting such laws. In South Africa, the Protection of Privacy Information Act (POPIA) was formally adopted in 2013 but it is yet to be implemented. When the implementation of the Act is announced, role players (responsible parties and data subjects) affected by POPIA will have a grace period of a year to become compliant and/or understand how the Act will affect them. One example of a mandate that follows from POPIA is data breach notification. This paper presents the development of a prototype ontology on POPIA to promote transparency and education of affected data subjects and organisations including government departments. The ontology provides a semantic representation of a knowledge base for the regulations in the POPIA and how it affects these role players. The POPIA is closely aligned with the European Union’s General Data Protection Regulation (GDPR), and the POPIA ontology is inspired by similar ontologies developed for the GDPR.
@{374, author = {Y Jafta, Louise Leenen, P Chan}, title = {An Ontology for the South African Protection of Personal Information Act}, abstract = {The protection and management of data, and especially personal information, is becoming an issue of critical importance in both the business environment and in general society. Various institutions have justifiable reasons to gather the personal information of individuals but they are required to comply with any legislation involving the processing of such data. Organisations thus face legal and other repercussions should personal information be breached or treated negligently. Most countries have adopted privacy and data protection laws or are in the process of enacting such laws. In South Africa, the Protection of Privacy Information Act (POPIA) was formally adopted in 2013 but it is yet to be implemented. When the implementation of the Act is announced, role players (responsible parties and data subjects) affected by POPIA will have a grace period of a year to become compliant and/or understand how the Act will affect them. One example of a mandate that follows from POPIA is data breach notification. This paper presents the development of a prototype ontology on POPIA to promote transparency and education of affected data subjects and organisations including government departments. The ontology provides a semantic representation of a knowledge base for the regulations in the POPIA and how it affects these role players. The POPIA is closely aligned with the European Union’s General Data Protection Regulation (GDPR), and the POPIA ontology is inspired by similar ontologies developed for the GDPR.}, year = {2020}, journal = {The 19th European Conference on Cyber Warfare and Security}, pages = {158 - 176}, month = {25/06 - 26/06}, publisher = {Academic Conferences and Publishing International Limited}, address = {UK}, isbn = {978-1-912764-61-7}, }
In the recent past, some Internet users questioned the reliability of online news, but not necessarily the role of search engines in programming public discourse. In 2018, South African Twitter users accused Google of peddling misinformation when Google Image searches for the phrase “squatter camps in South Africa” displayed images of white squatter camps. Many ana-lysts blamed Google’s algorithm for displaying bias. In this article, the authors use this example in comparing the findings of six different search engines to counter this argument. Search engines that are diverse in their scope and origin are used to prove that is it not the algorithm, but rather the data that is biased.
@article{373, author = {Jansen van Vuuren, Louise Leenen}, title = {Proving It Is the Data That Is Biased, Not the Algorithm Through a Recent South African Online Case Study}, abstract = {In the recent past, some Internet users questioned the reliability of online news, but not necessarily the role of search engines in programming public discourse. In 2018, South African Twitter users accused Google of peddling misinformation when Google Image searches for the phrase “squatter camps in South Africa” displayed images of white squatter camps. Many ana-lysts blamed Google’s algorithm for displaying bias. In this article, the authors use this example in comparing the findings of six different search engines to counter this argument. Search engines that are diverse in their scope and origin are used to prove that is it not the algorithm, but rather the data that is biased.}, year = {2020}, journal = {Journal of Information Warfare}, volume = {19}, pages = {118-129}, issue = {3}, publisher = {Peregrine Technical Solutions}, address = {Virginia, USA}, isbn = {1445-3312}, }
Cybercrime is increasing at a rate few individuals would have predicted. IBM estimated in 2016 that, in 2019, the cost of cybercrime would reach $2 trillion, a threefold increase from the 2015 estimate of $500 billion. The growth of the Internet and the rapid development of technology provide enormous economic and social benefits but at the same time provide platforms for cybercriminals to exploit. Organised crime is using more sophisticated techniques, which require highly skilled and specialised law enforcement responses. One example is the use of cryptocurrencies, which makes it easier for cybercriminals to hide their proceeds. Regulatory measures often lag behind.
In this paper, the authors give an overview of the growing threat of cybercrime with a specific focus on high levels of cybercrime in Africa. The focus then turns to the development of national cybercrime strategies and implementation. Results from literature and the authors’ analyses of two cyber indices to measure the capabilities and capacities of countries are combined to present a framework for the development of a cybercrime strategy, and in particular, a strategy customised for African countries.
@article{372, author = {Jansen van Vuuren, Louise Leenen, P Pieterse}, title = {Development and Implementation of Cybercrime Strategies in Africa with Specific Reference to South Africa}, abstract = {Cybercrime is increasing at a rate few individuals would have predicted. IBM estimated in 2016 that, in 2019, the cost of cybercrime would reach $2 trillion, a threefold increase from the 2015 estimate of $500 billion. The growth of the Internet and the rapid development of technology provide enormous economic and social benefits but at the same time provide platforms for cybercriminals to exploit. Organised crime is using more sophisticated techniques, which require highly skilled and specialised law enforcement responses. One example is the use of cryptocurrencies, which makes it easier for cybercriminals to hide their proceeds. Regulatory measures often lag behind. In this paper, the authors give an overview of the growing threat of cybercrime with a specific focus on high levels of cybercrime in Africa. The focus then turns to the development of national cybercrime strategies and implementation. Results from literature and the authors’ analyses of two cyber indices to measure the capabilities and capacities of countries are combined to present a framework for the development of a cybercrime strategy, and in particular, a strategy customised for African countries.}, year = {2020}, journal = {Journal of Information Warfare}, volume = {19}, pages = {83 - 101}, issue = {3}, publisher = {Peregrine Technical Solutions}, address = {Virginia, USA}, isbn = {1445-3312}, }
Cybersecurity is often incorrectly assumed to be a purely technical field; however, there are numerous multidisciplinary aspects, such as, for example, human factors, legal, and governance issues. The broad scope, combined with other historical or bureaucratic factors, can provide challenges to researchers and students where appropriate methodologies do not necessarily conform to traditional disciplinary norms; prejudice against research approaches can occur as a result of ‘old school thought’. This paper aims to investigate the South African national and institutional perspectives for higher education and research, identify challenges, and propose solutions to facilitate multidisciplinary research into cybersecurity and Information Warfare (IW) in South Africa.
@article{371, author = {T Ramluckan, B van Niekerk, Louise Leenen}, title = {Cybersecurity and Information Warfare Research in South Africa: Challenges and Proposed Solutions}, abstract = {Cybersecurity is often incorrectly assumed to be a purely technical field; however, there are numerous multidisciplinary aspects, such as, for example, human factors, legal, and governance issues. The broad scope, combined with other historical or bureaucratic factors, can provide challenges to researchers and students where appropriate methodologies do not necessarily conform to traditional disciplinary norms; prejudice against research approaches can occur as a result of ‘old school thought’. This paper aims to investigate the South African national and institutional perspectives for higher education and research, identify challenges, and propose solutions to facilitate multidisciplinary research into cybersecurity and Information Warfare (IW) in South Africa.}, year = {2020}, journal = {Journal of Information Warfare}, volume = {19}, pages = {80-95}, issue = {1}, publisher = {Peregrine Technical Solutions}, address = {Virginia, USA}, isbn = {ISSN 1445-3312}, }
Latest Research Publications:
TALKS:
1) 'What role can consciousness play in the building of artificial moral agents?' (CAIR/UP Symposium 2019);
2) 'Artificial moral agency: Philosophical challenges and design considerations' (FAIR 2018).
PUBLICATIONS:
1) Mabaso, B. A. (2020b). Computationally rational agents can be moral agents. 'Ethics and Information Technology'. doi:10.1007/s10676-020-09527-1;
2) Mabaso, B. A. (2020a). Artificial Moral Agents Within an Ethos of AI4SG. 'Philosophy and Technology'. doi:10.1007/s13347-020-00400-z.
Latest Research Publications:
DEGREES LINKED TO THIS RESEARCH GROUP:
1) 2020 - current PhD (Philosophy): (provisional title) 'Human Dignity as Deciding Factor for Artificial Morality';
2) 2018-2019 Master of Arts (Philosophy): 'Ethics of AI: Exploring a Virtue Ethics Framework for Lethal Autonomous Weapon Systems';
3) 2017 BA (Honours) (Philosophy): 'The Possibility of Ascribing Artificial Moral Agency: The Case of Self-driving Cars'.
TALKS:
1) 'Virtue ethics as a solution to artificial moral reasoning in the context of lethal autonomous weapon systems' (Forum for Artificial Intelligence Research (FAIR 2019));
2) 'Virtue ethics as a solution to artificial moral reasoning in the context of lethal autonomous weapon systems' (Fourth Industrial Revolution: Philosophical, Ethical and Legal Dimensions Conference 2019);
3) 'The use and abuse of autonomous weapons systems' (Amnesty International (UP Chapter) 2019 symposium);
4) 'An investigation on the moral status and use of Autonomous Weapons Systems in warfare' (PSSA 2019);
5) 'Responsible belief as a moral obligation and the quest for fair and transparent machine learning' (co-presented with Emma Ruttkamp-Bloem, Digital Humanities Southern Africa (DHASA));
6) 'Virtue ethics as a solution for artificial moral reasoning in autonomous weapons' (FAIR 2018);
7) Talks at CAIR/UP Symposium 2019 and 2018.
WORKSHOP ATTENDANCE:
1) 16-17 August 2018 – African states conference on nuclear weapons and autonomous weapons;
2) 09 July 2018 – African Seminar on lethal autonomous weapons systems.
Latest Research Publications:
DEGREES LINKED TO THIS RESEARCH GROUP:
1) 2017-2019 PhD (Philosophy): 'A Novel Reply to the Knowledge Argument: Wiredu’s View of Quasi-physicalism as a Positive Reply to Jackson'.
TALKS:
1) 'A response to Masaka, D. (2018) "Person, Personhood and Individual rights in Menkiti's African Communitarian thinking - Theoria 157, Vol 65. No 4' (APTA summer school- University of Fort Hare 1-4 December 2018);
2) 'Re-visiting the Chinese Room: A Response to Boden’s critique of Searle’s positive claim' (Philosophy postgraduate conference PPA 2018 - University of Pretoria);
3) 'A reflection on the knowledge problem for reductive physicalism and the impact of epistemic injustice on the quality of knowledge representation and reasoning in the context of the mind-body problem' (Humanities postgraduate conference 2019 - University of Pretoria);
4) 'A Novel response to the knowledge argument in support of non-reductive physicalism' (PSSA 2020 - University of KwaZulu-Natal).
Latest Research Publications:
Latest Research Publications: