A supervised learning approach based on STDP and polychronization in spiking neuron networks

We propose a novel network model of spiking neurons, without preimposed topology and driven by STDP (Spike-Time-Dependent Plasticity), a temporal Hebbian unsupervised learning mode, based on biological observations of synaptic plasticity. The model is further driven by a supervised learning algorithm, based on a margin criterion, that has effect on the synaptic delays linking the network to the output neurons, with classification as a goal task. The network processing and the resulting performance are completely explainable by the concept of polychronization, recently introduced by Izhikevich \cite{Izh06NComp}. On the one hand, our model can be viewed as a new machine learning concept for classifying patterns by means of spiking neuron networks. On the other hand, as a model of natural neural networks, it provides a new insight on cell assemblies, a fundamental notion for understanding the cognitive processes underlying memory. {\bf Keywords.} Spiking neuron networks, Synaptic plasticity, STDP, Delay learning, Classifier, Cell assemblies, Polychronous groups.