A Model-checking Approach to Reduce Spiking Neural Networks

Elisabetta De Maria, Daniel Gaffé, Cédric Girard Riboulleau, Annie Ressouche

2018

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.

Paper Citation

in Harvard Style

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 (BIOSTEC 2018) - Volume 3: BIOINFORMATICS; ISBN 978-989-758-280-6, SciTePress, pages 89-96. DOI: 10.5220/0006572000890096

in Bibtex Style

@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 (BIOSTEC 2018) - Volume 3: BIOINFORMATICS},
year={2018},
pages={89-96},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006572000890096},
isbn={978-989-758-280-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2018) - Volume 3: 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
PB - SciTePress