Skip to Main content Skip to Navigation
Master thesis

Modèles probabilistes et vérification de réseaux de neurones

Abstract : Research advances in the field of neurobiology imply that neural networks are becoming larger and more complex. However, this complexity increases the computation time of the model simulations and therefore the speed and the memory used by software. During this internship we choose to model neural networks as LI\&F models (Leaky Integrate and Fire) represented by Markov chains with PRISM, a probabilistic model checker. With this software, we have the possibility to include probability in spike emission in our models according to a sigmoid curve. After having implemented several network models containing different numbers of neurons, we test several properties encoded in PCTL (Probabilistic Computation Tree Logic). We established the pseudo-code of a reduction algorithm which takes as input a network and a property and gives as output a reduced network. This algorithm removes the "wall" neurons that block the transmission of the membrane potential and those whose suppression does not affect the output neurons or the topology of the network. The reduced networks obtained have a significantly lower complexity.
Document type :
Master thesis
Complete list of metadata

Cited literature [18 references]  Display  Hide  Download
Contributor : Annie Ressouche Connect in order to contact the contributor
Submitted on : Thursday, June 29, 2017 - 1:48:15 PM
Last modification on : Thursday, August 4, 2022 - 4:53:55 PM
Long-term archiving on: : Thursday, January 18, 2018 - 2:24:35 AM


  • HAL Id : hal-01550133, version 1



Cédric Girard Riboulleau. Modèles probabilistes et vérification de réseaux de neurones. Informatique et langage [cs.CL]. 2017. ⟨hal-01550133⟩



Record views


Files downloads