TS Artificial Neural Networks Classification: A Classification Approach based on Time & Signal

Fatima Zahrae Ait Omar, Najib Belkhayat

2018

Abstract

Artificial neural networks (ANN) have become the state-of-the-art technique to tackle highly complex problems in AI due to their high prediction and features’ extraction ability. The recent development in this technology has broadened the jungle of the existing ANNs architectures and caused the field to be less accessible to novices. It is increasingly difficult for new beginners to categorize the architectures and pick the best and well-suited ones for their study case, which makes the need to summarize and classify them undeniable. Many previous classifications tried to meet this aim but failed to clear up the use case for each architecture. The aim of this paper is to provide guidance and a clear overview to beginners and non-experts and help them choose the right architecture for their research without having to dig deeper in the field. The classification suggested for this purpose is performed according to two dimensions inspired of the brain’s perception of the outside world: the time scale upon which the data is collected and the signal nature.

Paper Citation

in Harvard Style

Omar F. and Belkhayat N. (2018). TS Artificial Neural Networks Classification: A Classification Approach based on Time & Signal. In Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2018) - Volume 1: KDIR; ISBN 978-989-758-330-8, SciTePress, pages 178-185. DOI: 10.5220/0006927701780185

in Bibtex Style

@conference{kdir18,
author={Fatima Zahrae Ait Omar and Najib Belkhayat},
title={TS Artificial Neural Networks Classification: A Classification Approach based on Time & Signal},
booktitle={Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2018) - Volume 1: KDIR},
year={2018},
pages={178-185},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006927701780185},
isbn={978-989-758-330-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2018) - Volume 1: KDIR
TI - TS Artificial Neural Networks Classification: A Classification Approach based on Time & Signal
SN - 978-989-758-330-8
AU - Omar F.
AU - Belkhayat N.
PY - 2018
SP - 178
EP - 185
DO - 10.5220/0006927701780185
PB - SciTePress