loading
Documents

Research.Publish.Connect.

Paper

Authors: Elisabetta De Maria 1 ; Daniel Gaffé 2 ; Cédric Girard Riboulleau 3 and Annie Ressouche 4

Affiliations: 1 Univ. Cote d’Azur, CNRS and I3S, France ; 2 Univ. Cote d’Azur, CNRS and LEAT, France ; 3 Univ. Cote d’Azur and INRIA SAM, France ; 4 INRIA SAM, France

ISBN: 978-989-758-280-6

ISSN: 2184-4305

Keyword(s): Neural Spiking Networks, Probabilistic Models, Temporal Logic, Model Checking, Network Reduction.

Related Ontology Subjects/Areas/Topics: Algorithms and Software Tools ; Bioinformatics ; Biomedical Engineering ; Systems Biology

Abstract: In this paper we formalize Boolean Probabilistic Leaky Integrate and Fire Neural Networks as Discrete-Time Markov Chains using the language PRISM. In our models, the probability for neurons to emit spikes is driven by the difference between their membrane potential and their firing threshold. The potential value of each neuron is computed taking into account both the current input signals and the past potential value. Taking advantage of this modeling, we propose a novel algorithm which aims at reducing the number of neurons and synaptical connections of a given network. The reduction preserves the desired dynamical behavior of the network, which is formalized by means of temporal logic formulas and verified thanks to the PRISM model checker.

PDF ImageFull Text

Download
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 35.168.112.145

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:
De Maria, E.; Gaffé, D.; Girard Riboulleau, C. and Ressouche, A. (2018). A Model-checking Approach to Reduce Spiking Neural Networks.In Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 3 BIOINFORMATICS: BIOINFORMATICS, ISBN 978-989-758-280-6, ISSN 2184-4305, pages 89-96. DOI: 10.5220/0006572000890096

@conference{bioinformatics18,
author={Elisabetta De Maria. and Daniel Gaffé. and Cédric Girard Riboulleau. and Annie Ressouche.},
title={A Model-checking Approach to Reduce Spiking Neural Networks},
booktitle={Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 3 BIOINFORMATICS: BIOINFORMATICS,},
year={2018},
pages={89-96},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006572000890096},
isbn={978-989-758-280-6},
}

TY - CONF

JO - Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 3 BIOINFORMATICS: BIOINFORMATICS,
TI - A Model-checking Approach to Reduce Spiking Neural Networks
SN - 978-989-758-280-6
AU - De Maria, E.
AU - Gaffé, D.
AU - Girard Riboulleau, C.
AU - Ressouche, A.
PY - 2018
SP - 89
EP - 96
DO - 10.5220/0006572000890096

Login or register to post comments.

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