F97: Ensembles and Cascading of Embedded Prototype Subspace Classifiers

Hast,A., Lind,M.

Abstract:
Deep learning approaches suffers from the so called interpretability problem and can therefore be very hard to visualise. Embedded Prototype Subspace Classifiers is one attempt in the field of explainable AI, which is both fast and efficient since it does not require repeated learning epochs and has no hidden layers. In this paper we investigate how well ensembles as well as cascading of such neural networks will perform on some popular datasets. The focus is on handwritten data such as digits, letters and signs. It is shown how cascading can be efficiently implemented in order to both increase accuracy as well as speed up the classification.