Browsing by Author "Lim, Nick Jin Sean"
Now showing items 1-5 of 5
-
A diversity-aware model for majority vote ensemble accuracy
(Addison-Wesley, 2020)Ensemble classifiers are a successful and popular approach for classification, and are frequently found to have better generalization performance than single models in practice. Although it is widely recognized that ... -
Linear dimensionality reduction in linear time: Johnson-Lindenstrauss-type guarantees for random subspace
(2017)We consider the problem of efficient randomized dimensionality reduction with norm-preservation guarantees. Specifically we prove data-dependent Johnson-Lindenstrauss-type geometry preservation guarantees for Ho's random ... -
Perceptual improvements for Super-Resolution of Satellite Imagery
(IEEE, 2021)Super-resolution of satellite imagery poses unique challenges. We propose a hybrid method comprising two existing deep network super-resolution approaches, namely a feedforward network called DeepSUM, and ESRGAN, a GAN-based ... -
Showcasing the TAIAO project: providing resources for machine learning from images of New Zealand's natural environment
(Informa UK Limited, 2022)Proper management of the earth's natural resources is imperative to combat further degradation of the natural environment. However, the environmental datasets necessary for informed resource planning and conservation can ... -
Studying and exploiting the relationship between model accuracy and explanation quality
(Springer, 2021)Many explanation methods have been proposed to reveal insights about the internal procedures of black-box models like deep neural networks. Although these methods are able to generate explanations for individual predictions, ...
Co-authors for Nick Jin Sean Lim
Supervised by Nick Jin Sean Lim
Showing up to 5 theses - most recently added to Research Commons first.
-
Super-resolution of satellite imagery
(The University of Waikato, 2021)Can deep neural networks super-resolve satellite imagery to a high perceptual quality? This thesis explores the juxtaposition between the pixel accuracy and perceptual qualities of super-resolved imagery by comparing and ...
