A supervised learning approach based on STDP and polychronization in spiking neuron networks
| Type of publication: | Idiap-RR |
| Citation: | paugam:rr06-54 |
| Number: | Idiap-RR-54-2006 |
| Year: | 2006 |
| Institution: | IDIAP |
| Abstract: | 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. |
| Userfields: | ipdmembership={learning}, |
| Keywords: | |
| Projects |
Idiap |
| Authors | |
| Crossref by |
paugam:esann:2007 |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
