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/2134/25474

Title: Online representation learning with single and multi-layer Hebbian networks for image classification tasks
Authors: Bahroun, Yanis
Soltoggio, Andrea
Keywords: Classification
Competitive learning
Feature learning
Hebbian learning
Online algorithm
Neural networks
Sparse coding
Unsupervised learning
Issue Date: 2017
Publisher: © Springer
Citation: BAHROUN, Y. and SOLTOGGIO, A., 2017. Online representation learning with single and multi-layer Hebbian networks for image classification tasks. IN: Lintas, A. ...et al. (eds.) Artificial Neural Networks and Machine Learning – ICANN 2017 26th International Conference on Artificial Neural Networks, Alghero, Italy, September 11-14, 2017, Proceedings, Part II. New York: Springer,
Series/Report no.: Lecture Notes in Computer Science; 10614
Abstract: Unsupervised learning permits the development of algorithms that are able to adapt to a variety of different datasets using the same underlying rules thanks to the autonomous discovery of discriminating features during training. Recently, a new class of Hebbian-like and local unsupervised learning rules for neural networks have been developed that minimise a similarity matching costfunction. These have been shown to perform sparse representation learning. This study tests the effectiveness of one such learning rule for learning features from images. The rule implemented is derived from a nonnegative classical multidimensional scaling cost-function, and is applied to both single and multi-layer architectures. The features learned by the algorithm are then used as input to an SVM to test their effectiveness in classification on the established CIFAR-10 image dataset. The algorithm performs well in comparison to other unsupervised learning algorithms and multi-layer networks, thus suggesting its validity in the design of a new class of compact, online learning networks.
Description: This paper was presented at the 26th International Conference on Artificial Neural Networks, Alghero, Sardinia, 11-15th September. This paper is in closed access until it is published.
Version: Accepted for publication
DOI: 10.1007/978-3-319-68612-7
URI: https://dspace.lboro.ac.uk/2134/25474
Publisher Link: http://www.springer.com/us/book/9783319686110
https://doi.org/10.1007/978-3-319-68612-7
ISBN: 9783319686110
ISSN: 0302-9743
Appears in Collections:Closed Access (Computer Science)

Files associated with this item:

File Description SizeFormat
ICANN2017_Single_Multi_preprint.pdfAccepted version889.39 kBAdobe PDFView/Open

 

SFX Query

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