TY - JOUR
T1 - Parameter estimation in spiking neural networks
T2 - A reverse-engineering approach
AU - Rostro-Gonzalez, H.
AU - Cessac, B.
AU - Vieville, T.
PY - 2012/4
Y1 - 2012/4
N2 - This paper presents a reverse engineering approach for parameter estimation in spiking neural networks (SNNs). We consider the deterministic evolution of a time-discretized network with spiking neurons, where synaptic transmission has delays, modeled as a neural network of the generalized integrate and fire type. Our approach aims at by-passing the fact that the parameter estimation in SNN results in a non-deterministic polynomial-time hard problem when delays are to be considered. Here, this assumption has been reformulated as a linear programming (LP) problem in order to perform the solution in a polynomial time. Besides, the LP problem formulation makes the fact that the reverse engineering of a neural network can be performed from the observation of the spike times explicit. Furthermore, we point out how the LP adjustment mechanism is local to each neuron and has the same structure as a 'Hebbian' rule. Finally, we present a generalization of this approach to the design of input-output (I/O) transformations as 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.
AB - This paper presents a reverse engineering approach for parameter estimation in spiking neural networks (SNNs). We consider the deterministic evolution of a time-discretized network with spiking neurons, where synaptic transmission has delays, modeled as a neural network of the generalized integrate and fire type. Our approach aims at by-passing the fact that the parameter estimation in SNN results in a non-deterministic polynomial-time hard problem when delays are to be considered. Here, this assumption has been reformulated as a linear programming (LP) problem in order to perform the solution in a polynomial time. Besides, the LP problem formulation makes the fact that the reverse engineering of a neural network can be performed from the observation of the spike times explicit. Furthermore, we point out how the LP adjustment mechanism is local to each neuron and has the same structure as a 'Hebbian' rule. Finally, we present a generalization of this approach to the design of input-output (I/O) transformations as 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.
KW - Timing-dependent plasticity
KW - Neurons
KW - Time
KW - Computation
KW - Precision
KW - Dynamics
KW - Systems
KW - Cortex
KW - Model
UR - http://www.scopus.com/inward/record.url?scp=84859139648&partnerID=8YFLogxK
UR - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=pure_univeritat_ramon_llull&SrcAuth=WosAPI&KeyUT=WOS:000302144100024&DestLinkType=FullRecord&DestApp=WOS_CPL
U2 - 10.1088/1741-2560/9/2/026024
DO - 10.1088/1741-2560/9/2/026024
M3 - Article
C2 - 22419215
AN - SCOPUS:84859139648
SN - 1741-2560
VL - 9
JO - Journal of Neural Engineering
JF - Journal of Neural Engineering
IS - 2
M1 - 026024
ER -