Back- engineering of spiking neural networks parameters

Horacio Rostro 1 Bruno Cessac 1, 2 Juan Carlos Vasquez 1 Thierry Viéville 3
CRISAM - Inria Sophia Antipolis - Méditerranée , INRIA Rocquencourt, ENS Paris - École normale supérieure - Paris, UNS - Université Nice Sophia Antipolis, CNRS - Centre National de la Recherche Scientifique : UMR8548
3 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : We consider the deterministic evolution of a time-discretized spiking network of neurons with connection weights having delays, modeled as a discretized neural network of the generalized integrate and fire (gIF) type. The purpose is to study a class of algorithmic methods allowing to calculate the proper parameters to reproduce exactly a given spike train generated by an hidden (unknown) neural network. This standard problem is known as NP-hard when delays are to be calculated. We propose here a reformulation, now expressed as a Linear-Programming (LP) problem, thus allowing to provide an efficient resolution. This allows us to ``back-engineer'' a neural network, i.e. to find out, given a set of initial conditions, which parameters (i.e., connection weights in this case), allow to simulate the network spike dynamics. More precisely we make explicit the fact that the back-engineering of a spike train, is a Linear (L) problem if the membrane potentials are observed and a LP problem if only spike times are observed, with a gIF model. Numerical robustness is discussed. We also explain how it is the use of a generalized IF neuron model instead of a leaky IF model that allows us to derive this algorithm. Furthermore, we point out how the L or LP adjustment mechanism is local to each unit and has the same structure as an ``Hebbian'' rule. A step further, this paradigm is easily generalizable to the design of input-output spike train transformations. This means that we have a practical method to ``program'' a spiking network, i.e. find a set of parameters allowing us to exactly reproduce the network output, given an input. Numerical verifications and illustrations are provided.
Type de document :
Communication dans un congrès
Eighteenth Annual Computational Neuroscience Meeting CNS*2009, 2009, Berlin, Germany. 2009
Liste complète des métadonnées
Contributeur : Thierry Viéville <>
Soumis le : lundi 27 juillet 2009 - 19:42:04
Dernière modification le : vendredi 12 janvier 2018 - 01:49:32


  • HAL Id : inria-00407911, version 1


Horacio Rostro, Bruno Cessac, Juan Carlos Vasquez, Thierry Viéville. Back- engineering of spiking neural networks parameters. Eighteenth Annual Computational Neuroscience Meeting CNS*2009, 2009, Berlin, Germany. 2009. 〈inria-00407911〉



Consultations de la notice