Feature Relevance Bounds for Linear Classification

Göpfert C, Pfannschmidt L, Hammer B (2017)
In: Proceedings of the ESANN, 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Verleysen M (Ed); Louvain-la-Neuve: Ciaco - i6doc.com: 187--192.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
OA 452.96 KB
OA es2017-67.pdf 1.62 MB
Herausgeber*in
Verleysen, Michele
Abstract / Bemerkung
Biomedical applications often aim for an identification of relevant features for a given classification task, since these carry the promise of semantic insight into the underlying process. For correlated input dimensions, feature relevances are not unique, and the identification of meaningful subtle biomarkers remains a challenge. One approach is to identify intervals for the possible relevance of given features, a problem related to all relevant feature determination. In this contribution, we address the important case of linear classifiers and we transfer the problem how to infer feature relevance bounds to a convex optimization problem. We demonstrate the superiority of the resulting technique in comparison to popular feature-relevance determination methods in several benchmarks.
Erscheinungsjahr
2017
Titel des Konferenzbandes
Proceedings of the ESANN, 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Seite(n)
187--192
Konferenz
25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)
Konferenzort
Bruges
Konferenzdatum
2017-04-26 – 2017-04-29
ISBN
978-287587039-1
Page URI
https://pub.uni-bielefeld.de/record/2908201

Zitieren

Göpfert C, Pfannschmidt L, Hammer B. Feature Relevance Bounds for Linear Classification. In: Verleysen M, ed. Proceedings of the ESANN, 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Louvain-la-Neuve: Ciaco - i6doc.com; 2017: 187--192.
Göpfert, C., Pfannschmidt, L., & Hammer, B. (2017). Feature Relevance Bounds for Linear Classification. In M. Verleysen (Ed.), Proceedings of the ESANN, 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (pp. 187--192). Louvain-la-Neuve: Ciaco - i6doc.com.
Göpfert, C., Pfannschmidt, L., and Hammer, B. (2017). “Feature Relevance Bounds for Linear Classification” in Proceedings of the ESANN, 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Verleysen, M. ed. (Louvain-la-Neuve: Ciaco - i6doc.com), 187--192.
Göpfert, C., Pfannschmidt, L., & Hammer, B., 2017. Feature Relevance Bounds for Linear Classification. In M. Verleysen, ed. Proceedings of the ESANN, 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Louvain-la-Neuve: Ciaco - i6doc.com, pp. 187--192.
C. Göpfert, L. Pfannschmidt, and B. Hammer, “Feature Relevance Bounds for Linear Classification”, Proceedings of the ESANN, 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, M. Verleysen, ed., Louvain-la-Neuve: Ciaco - i6doc.com, 2017, pp.187--192.
Göpfert, C., Pfannschmidt, L., Hammer, B.: Feature Relevance Bounds for Linear Classification. In: Verleysen, M. (ed.) Proceedings of the ESANN, 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. p. 187--192. Ciaco - i6doc.com, Louvain-la-Neuve (2017).
Göpfert, Christina, Pfannschmidt, Lukas, and Hammer, Barbara. “Feature Relevance Bounds for Linear Classification”. Proceedings of the ESANN, 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Ed. Michele Verleysen. Louvain-la-Neuve: Ciaco - i6doc.com, 2017. 187--192.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-25T06:40:59Z
MD5 Prüfsumme
1ef5ead8dcd2819e4e7513a287ab9868
Name
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-25T06:40:59Z
MD5 Prüfsumme
a01e375ae3a937e5cc7f8eca2cd1a15c

Link(s) zu Volltext(en)
Access Level
OA Open Access
Software:
Beschreibung
Link to source code used in publication

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar
ISBN Suche