Delay Learning and Polychronization for Reservoir Computing
Venue
Neurocomputing, vol. 71 (2008), pp. 1143-1158
Publication Year
2008
Authors
Hélène Paugam-Moisy, Régis Martinez, Samy Bengio
BibTeX
Abstract
We propose a multi-scale learning rule for spiking neuron networks, in the vein of
the recently emerging field of reservoir computing. The reservoir is a network
model of spiking neurons, with random topology and driven by STDP
(Spike-Time-Dependent Plasticity), a temporal Hebbian unsupervised learning mode,
biologically observed. The model is further driven by a supervised learning
algorithm, based on a margin criterion, that effects the synaptic delays linking
the network to the readout neurons, with classification as a goal task. The network
processing and the resulting performance can be explained by the concept of
polychronization, proposed by Izhikevich (2006, Neural Computation, 18,1), on
physiological bases. The model emphasizes the computational capabilities of this
concept.
