loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Basile Tousside ; Lukas Friedrichsen and Jörg Frochte

Affiliation: Bochum University of Applied Science, 42579 Heiligenhaus, Germany

Keyword(s): Tree-CNN, Continual Learning, Deep Learning, Hierarchical Classification, Robust.

Abstract: The ability to perform continual learning and the adaption to new tasks without losing the knowledge already acquired is still a problem that current machine learning models do not address well. This is a drawback, which needs to be tackled for different reasons. On the one hand, conserving knowledge without keeping all of the data over all tasks is a rising challenge with laws like the European General Data Protection Regulation. On the other hand, training models come along with CO2 footprint. In the spirit of a Green AI the reuse of trained models will become more and more important. In this paper we discuss a simple but effective approach based on a Tree-CNN architecture. It allows knowledge transfer from past task when learning a new task, which maintains the model compact despite network expansion. Second, it avoids forgetting, i.e., learning new tasks without forgetting previous tasks. Third, it is cheap to train, to evaluate and requires less memory compared to a single monol ithic model. Experimental results on a subset of the ImageNet dataset comparing different continual learning methods are presented. (More)

CC BY-NC-ND 4.0

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 3.146.34.148

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:
Tousside, B.; Friedrichsen, L. and Frochte, J. (2022). Towards Robust Continual Learning using an Enhanced Tree-CNN. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-547-0; ISSN 2184-433X, SciTePress, pages 316-325. DOI: 10.5220/0010819800003116

@conference{icaart22,
author={Basile Tousside. and Lukas Friedrichsen. and Jörg Frochte.},
title={Towards Robust Continual Learning using an Enhanced Tree-CNN},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2022},
pages={316-325},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010819800003116},
isbn={978-989-758-547-0},
issn={2184-433X},
}

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Towards Robust Continual Learning using an Enhanced Tree-CNN
SN - 978-989-758-547-0
IS - 2184-433X
AU - Tousside, B.
AU - Friedrichsen, L.
AU - Frochte, J.
PY - 2022
SP - 316
EP - 325
DO - 10.5220/0010819800003116
PB - SciTePress