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

Get full text

AI-based hybrid optimisation of multi-megawatt scale permanent magnet synchronous generators for offshore wind energy capture by Lilla, Abdurahman Daleel

“…The initial stage (STAGE I) of the hybrid optimisation utilised the DE algorithm. The objective function was set to reduce the initial cost (!"…”
Get full text

Bird song recognition with hidden Markov models by Van der Merwe, Hugo Jacobus

Get full text

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

“…This we use as a proof of concept that neural networks and, more generally, machine learning algorithms, endow physicists with powerful tools for the study of many-body localization and potentially other many-body physics problems.…”
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

Augmenting the action space with conventions to improve multi-agent cooperation in Hanabi by Bredell, Francois

Get full text

Machine learning in astronomy by Du Buisson, Lise

“…Using principal component analysis and linear discriminant analysis, we construct a grand total of 56 feature sets with which to train, optimise and test a Minimum Error Classifier (MEC), a naive Bayes classifier, a k-Nearest Neighbours (kNN) algorithm, a Support Vector Machine (SVM) and the SkyNet artificial neural network.…”
Get full text

Human action recognition with 3D convolutional neural networks by Cronje, Frans

“…Convolutional neural networks (CNNs) adapt the regular fully-connected neural network (NN) algorithm to facilitate image classification. Recently, CNNs have been demonstrated to provide superior performance across numerous image classification databases including large natural images (Krizhevsky et al., 2012). …”
Get full text

Person of interest rapid identification and tracking (POIRIT) assistance system by Arif, Danish

“…Additionally, the research considers environmental factors like fog and smog, incorporating the Retinex Algorithm with Wavelet transform for effective fog removal. …”
Get full text

Volatility Model Pricing and Calibration with Neural Networks using Bayesian Optimisation by Goosen, Jenna

“…Therefore, this dissertation explores the use of deep artificial neural networks to calibrate volatility models by deploying computational resources to train a model (offline) and then utilise the pre-trained model to competitively price options (online). …”
Get full text

ATOM : a distributed system for video retrieval via ATM networks by Roux, Matthew John

“…Having investigated four algorithms for rewind and fast-forward in the literature, a rewind and fast-forward algorithm is presented. …”
Get full text

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

Get full text

Tick-borne haemoparasite occurrence and Anaplasma bovis strain diversity in eastern rock sengis (Elephantulus myurus)

Get full text

Agricultural field boundary delineation using earth observation methods and multi-temporal Sentinel-2 imagery by Watkins, Barry

Get full text

Optimizing Battery Storage for Minimizing Forecast Errors in Wind Power Systems by Van der Merwe, Schalk Willem

Get full text

Development of a robust myoelectric control architecture for lower limb robotic prostheses applications. by Garikayi, Talon

Get full text

Improving methods for genotypic drug resistance testing in Mycobacterium tuberculosis by Mlamla, Zandile Cleopatra

Get full text

A comparative study of recurrent neural networks and statistical techniques for forecasting the stock prices of JSE-listed securities by Galant, Rushin

“…This is likely the result of the unforeseen impact of the covid-19 pandemic on financial markets that would not have been factored into the training sets of the machine learning algorithms. . . .…”
Get full text

Small-scale distributed machine learning in R by Taylor, Brenden

“…Machine learning models generally require large amounts of data to train and thus are computationally expensive, both in the absolute sense of actual compute time, and in the relative sense of the numerical complexity of the underlying calculations. …”
Get full text