Subword segmental neural language generation for Nguni languages by Meyer, Francois Rolihlahla

“…We propose subword segmental modelling, a neural architecture and training algorithm that learns subword segmentation during training. …”
Get full text

South African sign language dataset development and translation : a glove-based approach by Mcinnes, Ben

Get full text

A deep learning-based approach towards automating visual reinforced concrete bridge inspections by Dube, Bright N

“…Each model was built by first compiling defect images, labelling them according to defect/crack type and creating training and test sets at a 90-10% split. The training sets were then used to train the CNN models through transfer learning and fine-tuning using the fastai deep learning python library. …”
Get full text

Robust parameter estimation of finite mixture models with self-paced learning

Get full text

APIC: A method for automated pattern identification and classification by Goss, Ryan Gavin

“…This dissertation investigated the efficacy of a novel, general method for deploying ML in a variety of complex tasks, where best feature selection, data-set labelling, model definition and training processes were determined automatically. Models were developed in an iterative fashion, evaluated using both training and validation data sets. …”
Get full text

Dataset selection for aggregate model implementation in predictive data mining

Get full text
Get full text

Using question-specific vocabularies to support speech data collection with SALAAM by Chibuye, Kayokwa Nick

“…Speech-based Accent Learning And Articulation Mapping (SALAAM), a cross-language phoneme mapping algorithm was used to aid the study based on its implementation in an open-source tool Lex4All. …”
Get full text

Automated learning rates in machine learning for dynamic mini-batch sub-sampled losses

Get full text

Efficient Mixed-Order Hidden Markov Model Inference by Schwardt, Ludwig

Get full text

Artificial Neural Networks as a Probe of Many-Body Localization in Novel Topologies by Beetar, Cameron

“…The entanglement spectra of next-to-nearest-neighbour (J1 − J2, and, in particular, Majumdar-Ghosh) models, star models, and bicycle wheel models - without any further training of the artificial neural network - are classified. …”
Get full text

Language identification in a highly unbalanced dataset by Weber, Ian

Get full text

Machine learning methods for individual acoustic recognition in a species of field cricket by Dlamini, Gciniwe

“…Moreover, the performance of the deep learning models when trained upon the raw acoustic samples indicate that the feature (MFCC) extraction step can be bypassed; the deep learning machine algorithms can be trained directly on the raw acoustic data and still achieve great results.…”
Get full text

Online prognostic strategies with deep leaning models for fleets of engineering assets

Get full text

Protection-based Distributed Generation Penetration Limits on MV feeders - Using Machine Learning by Nxumalo, Emmanuel

“…A supervised machine learning algorithm is applied after nontrivial data pre-processing through recommendation systems and shuffling. …”
Get full text

Preparing teachers in developing for computational thinking teaching in primary education : a Namibian case study

Get full text
Get full text

Artificial neural networks and the cross-section of equity returns: identifying nonlinear opportunities on the Johannesburg Stock Exchange by Reed, Joshua

“…The activation function, training algorithm, learning rate, number of epochs, batch size, and loss function are kept constant across architectures. …”
Get full text

Data capture of geometric data for local authorities' geographic information systems by De Wet, Francois Johan

Get full text

Multiscale image representation in deep learning

Get full text

The modelling of IR emission spectra and solid rocket motor parameters using neural networks and partial least squares by Hamp, Niko

Get full text