Parameter Learning for Spiking Neural Networks Modelled as Timed Automata

Elisabetta De Maria, Cinzia Di Giusto

2018

Abstract

In this paper we present a novel approach to automatically infer parameters of spiking neural networks. Neurons are modelled as timed automata waiting for inputs on a number of different channels (synapses), for a given amount of time (the accumulation period). When this period is over, the current potential value is computed considering current and past inputs. If this potential overcomes a given threshold, the automaton emits a broadcast signal over its output channel, otherwise it restarts another accumulation period. After each emission, the automaton remains inactive for a fixed refractory period. Spiking neural networks are formalised as sets of automata, one for each neuron, running in parallel and sharing channels according to the network structure. This encoding is exploited to find an assignment for the synaptical weights of neural networks such that they can reproduce a given behaviour. The core of this approach consists in identifying some correcting actions adjusting synaptical weights and back-propagating them until the expected behaviour is displayed. A concrete case study is discussed.

Paper Citation

in Harvard Style

De Maria E. and Di Giusto C. (2018). Parameter Learning for Spiking Neural Networks Modelled as Timed Automata. 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 17-28. DOI: 10.5220/0006530300170028

in Bibtex Style

@conference{bioinformatics18,
author={Elisabetta De Maria and Cinzia Di Giusto},
title={Parameter Learning for Spiking Neural Networks Modelled as Timed Automata},
booktitle={Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2018) - Volume 3: BIOINFORMATICS},
year={2018},
pages={17-28},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006530300170028},
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 - Parameter Learning for Spiking Neural Networks Modelled as Timed Automata
SN - 978-989-758-280-6
AU - De Maria E.
AU - Di Giusto C.
PY - 2018
SP - 17
EP - 28
DO - 10.5220/0006530300170028
PB - SciTePress