Investigating the use of machine learning to value contingent claims

Get full text

Deep Learning-Based Brain Tumour Detection and Classification by Liza, Ansu

Get full text

Simulation of blood flows in a stenosed and bifurcating artery using finite volume methods and OpenFOAM by Nagarathnam, Sunitha

Get full text

On noise regularised neural networks: initialisation, learning and inference by Pretorius, Arnu

Get full text

Dirty learning : innovative teaching on the World Wide Web

Get full text

Nonlinear dynamics and chaos in multidimensional disordered Hamiltonian systems by Many, Manda Bertin

Get full text

School-based mechanisms of learner self-efficacy, engagement value and achievement : a structural equation analysis of grade 9 mathematics performance in South Africa by Takalani, Mukovhe Glen

Get full text

Walking the bridge from single- to multi-species approaches in Southern African fisheries management by Plaganyi-Lloyd, Eva Elizabeth

“…Strengths include the structured parameterisation :framework, the inclusion of a well-balanced level of conceptual realism, a novel representation of predator-prey interaction terms and the inclusion of a Bayes-like approach (ECORANGER) to take account of the uncertainty associated with values for model inputs. The potential of EwE to contribute to five important multi-species management quandaries in the marine environments off southern Africa and Antarctica is assessed, leading to the conclusion that EwE has limited predictive capability in these contexts. 3 Aspects of the potential application of other multi-species/ecosystem modelling approaches to advise the management of South African fisheries are discussed. …”
Get full text

The eco-evolutionary dynamics of mutualistic networks: from pattern of emergence to stability by Minoarivelo, Henintsoa Onivola

Get full text

Unravelling black box machine learning methods using biplots by Rowan, Adriaan

“…Following the development of new mathematical techniques, the improvement of computer processing power and the increased availability of possible explanatory variables, the financial services industry is moving toward the use of new machine learning methods, such as neural networks, and away from older methods such as generalised linear models. …”
Get full text

Modelling uranium leaching kinetics

Get full text

Investigating fully convolutional networks for bio-image segmentation by Wiehman, Stiaan

Get full text

Extended theories of gravity: the early universe and stellar interiors by Campbell, Mariam

“…This thesis explores two central themes within extended theories of general relativity: the cosmological dynamics of the early universe and the formulation of mathematical frameworks for modeling relativistic stars, with the overarching aim of testing and constraining model parameters in modified gravity. …”
Get full text

Steinberg algebra and Leavitt path algebras by Rigby, Simon W

Get full text

Multitask learning and data distribution search in visual relationship recognition by Josias, Shane

Get full text

The application of neural differential equations to enzymatic time-series by Heusdens, Danica Aimee

Get full text

Mobile devices in a blended learning environment in higher education

Get full text

Activities of champions implementing e-Learning processes in higher education

Get full text
Get full text

Enhanced LSMC for Valuation of Options by Mekawy, Amr

Get full text
Get full text
Get full text
Get full text