Spiking Neural Networks modelled as Timed Automata with parameter learning - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2018

Spiking Neural Networks modelled as Timed Automata with parameter learning

Elisabetta de Maria
  • Fonction : Auteur
  • PersonId : 170153
  • IdHAL : edemaria
Cinzia · Di Giusto
Laetitia Laversa

Résumé

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 (synap-ses), 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. Such a model is formally validated against some crucial properties defined via proper temporal logic formu-lae. The model is then 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.
Fichier principal
Vignette du fichier
mainjournal.pdf (498.46 Ko) Télécharger le fichier
svglov3.clo (3.72 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01812544 , version 1 (12-06-2018)

Identifiants

Citer

Elisabetta de Maria, Cinzia · Di Giusto, Laetitia Laversa. Spiking Neural Networks modelled as Timed Automata with parameter learning. 2018. ⟨hal-01812544⟩
35 Consultations
188 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More