Title: | Ensembles and Cascading of Embedded Prototype Subspace Classifiers |
Authors: | Hast, Anders Lind, Mats |
Citation: | Journal of WSCG. 2020, vol. 28, no. 1-2, p. 89-95. |
Issue Date: | 2020 |
Publisher: | Václav Skala - UNION Agency |
Document type: | článek article |
URI: | http://wscg.zcu.cz/WSCG2020/2020-J_WSCG-1-2.pdf http://hdl.handle.net/11025/38429 |
ISSN: | 1213-6972 (print) 1213-6980 (CD-ROM) 1213-6964 (on-line) |
Keywords: | podprostory;soubory;kaskádování;vložené prototypy;neuronové sítě;hluboké učení |
Keywords in different language: | subspaces;ensembles;cascading;embedded prototypes;neural networks;deep learning |
Abstract in different language: | Deep learning approaches suffer 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 ensembles and cascades of ensembles 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. |
Rights: | © Václav Skala - UNION Agency |
Appears in Collections: | Volume 28, Number 1-2 (2020) |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/38429
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.