Search
Now showing items 1-10 of 10
Domain adaptation for speaker diarisation in low-resource environments
(North-West University (South Africa)., 2022)
Speaker diarisation systems aim to answer the question \who spoke when?" and are useful
in providing valuable metadata to downstream applications, such as automatic speech
recognition systems. However, speaker diarisation ...
Activation functions in deep neural networks
(North-West University (South Africa), 2020)
The ability of machine learning algorithms to generalize is arguably their most important aspect as it determines their ability to perform appropriately on unseen data. The impres-sive generalization abilities of deep ...
Exploring data utilisation in neural networks
(North-West University (South Africa)., 2022)
The generalisation ability of deep neural networks differs somewhat from that of more
traditional models. Speciőcally, large networks that have the ability to łmemorisež the
training data can still generalise well, ...
Automatic speech recognition of poor quality audio using generative adversarial networks
(North-West University (South Africa)., 2022)
In this study, we investigate the use of generative adversarial networks (GANs) to improve
speech recognition performance of poor quality audio obtained from a real-world source.
A GAN is developed to transform acoustic ...
Generalization in deep learning : bilateral synergies in MLP learning
(North-West University (South Africa)., 2021)
We present an investigation of how simple artificial neural networks (specifcally, feed-forward
networks with full connections between each successive pair of layers) generalize to
out-of-sample data. By emphasizing the ...
Interpretability of deep neural networks for SYM-H prediction
(North-West University (South Africa), 2021)
Deep neural networks (DNNs) have shown impressive performance on a wide variety of
applications, but it remains di cult to interpret these models. For regression modelling,
DNNs generally do not explicitly provide any ...
Interpreting deep neural networks with sample sets
(North-West University (South Africa)., 2022)
Despite their impressive performances on a range of widespread tasks, deep neural networks
(DNNs) are generally considered `black box' models due to the lack of transparency
behind their decision-making processes. ...
Parametric studies of translation invariance and distortion robustness in Convolutional Neural Networks
(North-West University (South Africa), 2021)
Although Convolutional Neural Networks (CNNs) are widely used, their translation in-variance (ability to deal with translated inputs) is still subject to some controversy. We explore this question using translation-sensitivity ...
Deep neural networks for prediction of solar flares
(North-West University (South Africa), 2021)
Solar flares are enormous explosions on the solar surface that originates from sunspots, which could cause damage to satellites, power grids and radio communication systems. Having early-warning systems that could accurately ...
Contrasting Convolutional Neural Networks with alternative architectures for transformation invariance
(North-West University (South Africa), 2021)
Convolutional Neural Networks (CNNs) have become the standard for image classification tasks, however, they are not completely invariant to transformations of the input image. We empirically investigate to which degree CNNs ...