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

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. Key words: Support feature machine, feature selection, zero norm minimisation, classification.

• Type: Journal
• Year: 2010
• Where: ICANN
• Authors: Sascha Klement, Thomas Martinetz
• Keywords: ICANN 2010, Inherent Feature Selection, Neural Networks, Separating Hyperplane, Zero Norm