Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/26825

Title: Neural networks for efficient nonlinear online clustering
Authors: Bahroun, Yanis
Hunsicker, Eugenie
Soltoggio, Andrea
Keywords: Nonlinear kernel
Clustering
Hebbian learning
Neural networks
Issue Date: 2017
Publisher: © Springer
Citation: BAHROUN, Y., HUNSICKER, E. and SOLTOGGIO, A., 2017. Neural networks for efficient nonlinear online clustering. To appear in: Proceedings of the 24th International Conference on Neural Information Processing (ICONIP 2017), Guangzhou, China, 14-18 November 2017.
Abstract: Unsupervised learning techniques, such as clustering and sparse coding, have been adapted for use with data sets exhibiting nonlinear relationships through the use of kernel machines. These techniques often require an explicit computation of the kernel matrix, which becomes expensive as the number of inputs grows, making it unsuitable for efficient online learning. This paper proposes an algorithm and a neural architecture for online approximated nonlinear kernel clustering using any shift-invariant kernel. The novel model outperforms traditional low-rank kernel approximation based clustering methods, it also requires significantly lower memory requirements than those of popular kernel k-means while showing competitive performance on large data sets.
Description: This conference paper is closed access until 12 months after the date of publication.
Version: Accepted for publication
URI: https://dspace.lboro.ac.uk/2134/26825
Publisher Link: http://www.iconip2017.org/
Appears in Collections:Closed Access (Computer Science)

Files associated with this item:

File Description SizeFormat
ICONIP2017_YB_cameraReady.pdfAccepted version436.08 kBAdobe PDFView/Open

 

SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.