Sign in to your account

Group Members

Faculty

Benjamin Rosman

RAIL Lab Director - Reinforcement Learning | Intelligent Robotics | Deep Learning

Chris Cleghorn

Stochastic Optimization | Neural Networks | Applications of AI to Radio Astronomy

Research Associates

PhD Candidates

Jonathan Gerrand

Electrical Engineer | Data scientist at Explore-AI | Intelligent systems for Healthcare

Geethen Singh

Computer vision using satellite data for invasive species management

Beatrice van Eden

PhD candidate at the University of the Witwatersrand. R&D Engineer of the Council for Scientific and Industrial Research (CSIR).

MSc Candidates

Aneesh Chandran

Reinforcement Learning for Anticipatory cobots in an industrial setting

Chris Fourie

Machine learning, Theoretical / Computational Neuroscience, Healthcare

Alumni

PhD Students

  • Steve James (2021) - Learning Portable Symbolic Representations
  • Ofir Marom (2021) - Leveraging Prior Knowledge for Sample Efficient Reinforcement Learning
  • Orhan Can Görür (2020) - Social Cobots: Anticipatory Decision-Making for Collaborative Robots with Extended Human Adaptation
  • Adam Earle (2019) - Spectral Reinforcement Learning
  • Ashley Kleinhans (2019) - Robotic grasping inspired by neuroscience using tools developed for deep learning
  • Ritesh Ajoodha (2018) - Influence modelling and learning between dynamic Bayesian networks using score-based structure learning
  • Ndivhuwo Makondo (2018) - Accelerating robot learning of motor skills with knowledge transfer
  • Pravesh Ranchod (2018) - Skill Discovery from Multiple Related Demonstrators

MSc Students

  • Gerrie Crafford (2021) - Improving reinforcement learning with ensembles of different learners
  • Leroy Dunn (2021) - Efficient Curriculum Generation for Reinforcement Learning
  • Devon Jarvis (2021) - Generalizing Regularization of Neural Networks to Correlated Parameter Spaces
  • Nishai Kooverjee (2021) - How does relational knowledge generalise? An analysis of transfer learning for graph neural networks
  • Iordan Tchaparov (2021) - Enabling Collaboration with Intention Inference using Partially Observable Markov Decision Processes
  • Kale-ab Tessera (2021) - On Sparsity in Deep Learning: The Benefits and Pitfalls of Sparse Neural Networks and How to Learn Their Architectures
  • Tlou Bokola (2020) - Knowledge Transfer Using Model-based Deep Reinforcement Learning
  • Roy Eyono (2020) - Learning to Backpropagate
  • Yongama Feni (2020) - Evaluating the Reliability of Quantification Results
  • Shahil Mawjee (2020) - Progressive option extraction with a curriculum of tasks
  • Liron Mizrahi (2020) - Using social context for person re-identification
  • Raesetje Sefala (2020) - Using satellite images and computer vision to study the evolution and effects of spatial apartheid in South Africa
  • Isaac Tarume (2020) - Study of Anomaly Detection in Diverse Populations using Probabilistic Graphical Models
  • Craig Bester (2019) - Multi-Pass Deep Q-Networks for Reinforcement Learning with Parameterised Action Spaces
  • Menzi Mthwecu (2019) - Efficient Search and Tracking for Non-Stationary Targets
  • Benjamin van Niekerk (2019) - Learning Safe Predictive Control with Gaussian Processes
  • Sicelukwanda Zwane (2019) - Using Mixture Density Networks to Model Continuous Action Priors
  • Richard Fisher (2018) - Topology-inspired Probabilistic Path Replanning in Dynamic Environments
  • Jason Perlow (2018) - Raw Material Selection for Object Construction
  • Ntokozo Mabena (2017) - Accelerating Decision Making Under Partial Observability Using Learned Action Priors
  • Michihisa Hiratsuka (2016) - Incremental Learning of Smoothed Dynamic Motion Primitives from Demonstration
  • Steve James (2016) - The Effect of Simulation Bias on Action Selection in Monte Carlo Tree Search
  • Phumlani Khoza (2016) - Electroencephalography brain computer interface using an asynchronous protocol
  • Jeremy Lai Hong (2016) - Adaptive Knowledge Injection for Monte Carlo Tree Search for Imperfect Information Games