Now showing items 1-5 of 5

    • Benign interpolation of noise in deep learning 

      Davel, Marelie Hattingh; Barnard, Etienne; Theunissen, Marthinus Wilhelmus (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, ...
    • Pairwise networks for feature ranking of a geomagnetic storm model 

      Beukes, Jacques Pieter; Davel, Marelie Hattingh; Lotz, Stefan (South African Institute of Computer Scientists and Information Technologists, 2020)
      Feedforward neural networks provide the basis for complex regression models that produce accurate predictions in a variety of applications. However, they generally do not explicitly provide any information about the utility ...
    • Pre-interpolation loss behavior in neural networks 

      Venter, Arthur Edgar William; Theunissen, Marthinus Wilhelm; Davel, Marelie Hattingh (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 ...
    • The South African directory enquiries (SADE) name corpus 

      Thirion, Jan Willem Frederick; Van Heerden, Charl Johannes; Giwa, Oluwapelumi; Davel, Marelie Hattingh (Springer, 2020)
      We present the design and development of a South African directory enquiries (DE) corpus. It contains audio and orthographic transcriptions of a wide range of South African names produced by first language speakers of four ...
    • Using summary layers to probe neural network behaviour 

      Davel, Marelie Hattingh (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 ...