loading
Documents

Research.Publish.Connect.

Paper

Authors: Hlynur Hlynsson ; Alberto Escalante-B. and Laurenz Wiskott

Affiliation: Ruhr University Bochum, Universitätsstraße 150, 44801 Bochum, Germany

ISBN: 978-989-758-351-3

Keyword(s): Data Efficiency, Deep Learning, Neural Networks, Slow Feature Analysis, Transfer Learning.

Abstract: In this paper, we propose a new experimental protocol and use it to benchmark the data efficiency — performance as a function of training set size — of two deep learning algorithms, convolutional neural networks (CNNs) and hierarchical information-preserving graph-based slow feature analysis (HiGSFA), for tasks in classification and transfer learning scenarios. The algorithms are trained on different-sized subsets of the MNIST and Omniglot data sets. HiGSFA outperforms standard CNN networks when the models are trained on 50 and 200 samples per class for MNIST classification. In other cases, the CNNs perform better. The results suggest that there are cases where greedy, locally optimal bottom-up learning is equally or more powerful than global gradient-based learning.

PDF ImageFull Text

Download
Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 34.229.151.87

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Hlynsson, H.; Escalante-B., A. and Wiskott, L. (2019). Measuring the Data Efficiency of Deep Learning Methods.In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-351-3, pages 691-698. DOI: 10.5220/0007456306910698

@conference{icpram19,
author={Hlynur Davíð Hlynsson. and Alberto N. Escalante{-}B.. and Laurenz Wiskott.},
title={Measuring the Data Efficiency of Deep Learning Methods},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2019},
pages={691-698},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007456306910698},
isbn={978-989-758-351-3},
}

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Measuring the Data Efficiency of Deep Learning Methods
SN - 978-989-758-351-3
AU - Hlynsson, H.
AU - Escalante-B., A.
AU - Wiskott, L.
PY - 2019
SP - 691
EP - 698
DO - 10.5220/0007456306910698

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.