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/2134/25475

Title: Building efficient deep Hebbian networks for image classification tasks
Authors: Bahroun, Yanis
Hunsicker, Eugenie
Soltoggio, Andrea
Keywords: Sparse coding
Dimensionality reduction
Hebbian/anti-Hebbian learning
MultiDimensional scaling
Biologically plausible learning rules
Issue Date: 2017
Publisher: © Springer
Citation: BAHROUN, Y., HUNSICKER, E. and SOLTOGGIO, A., 2017. Building efficient deep 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 I. New York: Springer, pp. 364-372.
Series/Report no.: Lecture Notes in Computer Science; 10614
Abstract: Multi-layer models of sparse coding (deep dictionary learning) and dimensionality reduction (PCANet) have shown promise as unsupervised learning models for image classification tasks. However, the pure implementations of these models have limited generalisation capabilities and high computational cost. This work introduces the Deep Hebbian Network (DHN), which combines the advantages of sparse coding, dimensionality reduction, and convolutional neural networks for learning features from images. Unlike in other deep neural networks, in this model, both the learning rules and neural architectures are derived from cost-function minimizations. Moreover, the DHN model can be trained online due to its Hebbian components. Different configurations of the DHN have been tested on scene and image classification tasks. Experiments show that the DHN model can automatically discover highly discriminative features directly from image pixels without using any data augmentation or semi-labeling.
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 27th Oct 2018.
Version: Accepted for publication
URI: https://dspace.lboro.ac.uk/2134/25475
Publisher Link: http://www.springer.com/us/book/9783319686110
ISBN: 9783319686110
ISSN: 0302-9743
Appears in Collections:Conference Papers and Presentations (Maths)
Closed Access (Computer Science)

Files associated with this item:

File Description SizeFormat
ICANN2017_DHN_preprint.pdfAccepted version315.54 kBAdobe PDFView/Open


SFX Query

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