ICANN2017_DHN_preprint.pdf (315.54 kB)
Building efficient deep Hebbian networks for image classification tasks
conference contribution
posted on 2017-06-20, 12:42 authored by Yanis Bahroun, Eugenie Hunsicker, Andrea SoltoggioAndrea SoltoggioMulti-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.
History
School
- Science
Department
- Computer Science
Published in
International Conference on Artificial Neural NetworksCitation
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.Publisher
© SpringerVersion
- AM (Accepted Manuscript)
Publisher statement
This work is made available according to the conditions of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) licence. Full details of this licence are available at: https://creativecommons.org/licenses/by-nc-nd/4.0/Acceptance date
2017-05-31Publication date
2017Notes
This paper was presented at the 26th International Conference on Artificial Neural Networks, Alghero, Sardinia, 11-15th September. This is a pre-copyedited version of a contribution published in Lintas, A. ...et al. (eds.) Artificial Neural Networks and Machine Learning – ICANN 2017 published by Springer. The definitive authenticated version is available online via https://doi.org/10.1007/978-3-319-68612-7.ISBN
9783319686110ISSN
0302-9743Publisher version
Book series
Lecture Notes in Computer Science; 10614Language
- en