3 papers
stat.ML2020
Fundamental Issues Regarding Uncertainties in Artificial Neural Networks
Neil A. Thacker, Carole J. Twining, Paul D. Tar +2
Artificial Neural Networks (ANNs) implement a specific form of multi-variate extrapolation and will generate an output for any input pattern, even when there is no similar training…
cs.CV2020
Evaluating Registration Without Ground Truth
Carole J. Twining, Vladimir S. Petrović, Timothy F. Cootes +3
We present a generic method for assessing the quality of non-rigid registration (NRR) algorithms, that does not depend on the existence of any ground truth, but depends solely on t…
stat.ME2015
Principal Autoparallel Analysis: Data Analysis in Weitzenböck Space
Stephen Marsland, Carole J Twining
The statistical analysis of data lying on a differentiable, locally Euclidean, manifold introduces a variety of challenges because the analogous measures to standard Euclidean stat…