Browsing by Subject "Deep Learning"
Now showing items 1-5 of 5
-
Benign interpolation of noise in deep learning
(South African Institute of Computer Scientists and Information Technologists, 2020)The understanding of generalisation in machine learning is in a state of flux, in part due to the ability of deep learning models to interpolate noisy training data and still perform appropriately on out-of-sample data, ... -
Employing case studies to develop professional skills in South African accountancy students: a comparative follow-up study
(Clute Institute, 2016)Some of the main challenges faced in accounting education are developing professional skills and encouraging deep learning in students. The literature offers numerous accounts of the case study method as a successful tool ... -
Pre-interpolation loss behavior in neural networks
(Springer, 2020)When training neural networks as classifiers, it is common to observe an increase in average test loss while still maintaining or improving the overall classification accuracy on the same dataset. In spite of the ubiquity ... -
Tracking translation invariance in CNNs
(Southern African Conference for Artificial Intelligence Research, 2020)Although Convolutional Neural Networks (CNNs) are widely used, their translation invariance (ability to deal with translated inputs) is still subject to some controversy. We explore this question using translation-sensitivity ... -
Using summary layers to probe neural network behaviour
(South African Institute of Computer Scientists and Information Technologists, 2020)No framework exists that can explain and predict the generalisation ability of deep neural networks in general circumstances. In fact, this question has not been answered for some of the least complicated of neural network ...
