The Support Feature Machine for Classifying with the Least Number of Features

Sascha Klement; Thomas Martinetz

doi:10.1007/978-3-642-15822-3_11

The Support Feature Machine for Classifying with the Least Number of Features

Sascha Klement, Thomas Martinetz

Institute of Neuro- and Bioinformatics

6 Citations (Scopus)

Abstract

We propose the so-called Support Feature Machine (SFM) as a novel approach to feature selection for classification, based on minimisation of the zero norm of a separating hyperplane. Thus, a classifier with inherent feature selection capabilities is obtained within a single training run. Results on toy examples demonstrate that this method is able to identify relevant features very effectively.

Original language	English
Title of host publication	Artificial Neural Networks -- ICANN 2010
Editors	Konstantinos Diamantaras, Wlodek Duch, Lazaros S. Iliadis
Number of pages	6
Volume	6353
Place of Publication	Berlin, Heidelberg
Publisher	Springer Berlin Heidelberg
Publication date	2010
Pages	88-93
ISBN (Print)	978-3-642-15821-6
ISBN (Electronic)	978-3-642-15822-3
DOIs	https://doi.org/10.1007/978-3-642-15822-3_11
Publication status	Published - 2010
Event	20th International Conference Artificial Neural Networks - Thessaloniki, Greece Duration: 15.09.2010 → 18.09.2010

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being
SDG 9 Industry, Innovation, and Infrastructure

Access to Document

10.1007/978-3-642-15822-3_11

KlMa10Final published version, 84 KB

Cite this

@inproceedings{1380ae9541d949bab3f536e133198730,

title = "The Support Feature Machine for Classifying with the Least Number of Features",

abstract = "We propose the so-called Support Feature Machine (SFM) as a novel approach to feature selection for classification, based on minimisation of the zero norm of a separating hyperplane. Thus, a classifier with inherent feature selection capabilities is obtained within a single training run. Results on toy examples demonstrate that this method is able to identify relevant features very effectively.",

author = "Sascha Klement and Thomas Martinetz",

year = "2010",

doi = "10.1007/978-3-642-15822-3\_11",

language = "English",

isbn = "978-3-642-15821-6",

volume = "6353",

series = "Lecture Notes in Computer Science",

publisher = "Springer Berlin Heidelberg",

pages = "88--93",

editor = "Konstantinos Diamantaras and Wlodek Duch and Iliadis, \{Lazaros S.\}",

booktitle = "Artificial Neural Networks -- ICANN 2010",

note = "20th International Conference Artificial Neural Networks<br/>, ICANN 2010 ; Conference date: 15-09-2010 Through 18-09-2010",

}

Klement, S & Martinetz, T 2010, The Support Feature Machine for Classifying with the Least Number of Features. in K Diamantaras, W Duch & LS Iliadis (eds), Artificial Neural Networks -- ICANN 2010. vol. 6353, Lecture Notes in Computer Science, vol. 6353, Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 88-93, 20th International Conference Artificial Neural Networks
, Thessaloniki, Greece, 15.09.10. https://doi.org/10.1007/978-3-642-15822-3_11

The Support Feature Machine for Classifying with the Least Number of Features. / Klement, Sascha; Martinetz, Thomas.
Artificial Neural Networks -- ICANN 2010. ed. / Konstantinos Diamantaras; Wlodek Duch; Lazaros S. Iliadis. Vol. 6353 Berlin, Heidelberg: Springer Berlin Heidelberg, 2010. p. 88-93 (Lecture Notes in Computer Science; Vol. 6353).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - The Support Feature Machine for Classifying with the Least Number of Features

AU - Klement, Sascha

AU - Martinetz, Thomas

PY - 2010

Y1 - 2010

N2 - We propose the so-called Support Feature Machine (SFM) as a novel approach to feature selection for classification, based on minimisation of the zero norm of a separating hyperplane. Thus, a classifier with inherent feature selection capabilities is obtained within a single training run. Results on toy examples demonstrate that this method is able to identify relevant features very effectively.

AB - We propose the so-called Support Feature Machine (SFM) as a novel approach to feature selection for classification, based on minimisation of the zero norm of a separating hyperplane. Thus, a classifier with inherent feature selection capabilities is obtained within a single training run. Results on toy examples demonstrate that this method is able to identify relevant features very effectively.

U2 - 10.1007/978-3-642-15822-3_11

DO - 10.1007/978-3-642-15822-3_11

M3 - Conference contribution

SN - 978-3-642-15821-6

VL - 6353

T3 - Lecture Notes in Computer Science

SP - 88

EP - 93

BT - Artificial Neural Networks -- ICANN 2010

A2 - Diamantaras, Konstantinos

A2 - Duch, Wlodek

A2 - Iliadis, Lazaros S.

PB - Springer Berlin Heidelberg

CY - Berlin, Heidelberg

T2 - 20th International Conference Artificial Neural Networks<br/>

Y2 - 15 September 2010 through 18 September 2010

ER -

The Support Feature Machine for Classifying with the Least Number of Features

Abstract

UN SDGs

Access to Document

Fingerprint

Cite this