MAXIMUM TOLERANCE AND MAXIMUM GREATEST TOLERANCE - Weights and Threshold of Strict Separating Systems

J. Freixas, X. Molinero

2010

Abstract

An important consideration when applying neural networks is the sensitivity to weights and threshold in strict separating systems representing a linearly separable function. Two parameters have been introduced to measure the relative errors in weights and threshold of strict separating systems: the tolerance and the greatest tolerance. Given an arbitrary separating system we study which is the equivalent separating system that provides maximum tolerance or/and maximum greatest tolerance.

Paper Citation

in Harvard Style

Freixas J. and Molinero X. (2010). MAXIMUM TOLERANCE AND MAXIMUM GREATEST TOLERANCE - Weights and Threshold of Strict Separating Systems . In Proceedings of the 2nd International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-674-021-4, pages 511-514. DOI: 10.5220/0002706905110514

in Bibtex Style

@conference{icaart10,
author={J. Freixas and X. Molinero},
title={MAXIMUM TOLERANCE AND MAXIMUM GREATEST TOLERANCE - Weights and Threshold of Strict Separating Systems},
booktitle={Proceedings of the 2nd International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2010},
pages={511-514},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002706905110514},
isbn={978-989-674-021-4},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - MAXIMUM TOLERANCE AND MAXIMUM GREATEST TOLERANCE - Weights and Threshold of Strict Separating Systems
SN - 978-989-674-021-4
AU - Freixas J.
AU - Molinero X.
PY - 2010
SP - 511
EP - 514
DO - 10.5220/0002706905110514