%Aigaion2 BibTeX export from Idiap Publications %Thursday 21 November 2024 12:15:07 PM @INPROCEEDINGS{paugam:esann:2007, author = {Paugam-Moisy, H{\'{e}}l{\`{e}}ne and Martinez, R. and Bengio, Samy}, projects = {Idiap}, title = {A supervised learning approach based on {STDP} and polychronization in spiking neuron networks}, booktitle = {European Symposium on Artificial Neural Networks, {ESANN}}, year = {2007}, note = {IDIAP-RR 06-54}, crossref = {paugam:rr06-54}, abstract = {We propose a network model of spiking neurons, without preimposed 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 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, proposed by Izhikevich~\cite{Izh06NComp}. The model emphasizes the computational capabilities of this concept.}, pdf = {https://publications.idiap.ch/attachments/papers/2007/paugam-esann-2007.pdf}, postscript = {ftp://ftp.idiap.ch/pub/papers/2007/paugam-esann-2007.ps.gz}, ipdmembership={learning}, } crossreferenced publications: @TECHREPORT{paugam:rr06-54, author = {Paugam-Moisy, H{\'{e}}l{\`{e}}ne and Martinez, R. and Bengio, Samy}, projects = {Idiap}, title = {A supervised learning approach based on {STDP} and polychronization in spiking neuron networks}, type = {Idiap-RR}, 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.}, pdf = {https://publications.idiap.ch/attachments/reports/2006/paugam-idiap-rr-06-54.pdf}, postscript = {ftp://ftp.idiap.ch/pub/reports/2006/paugam-idiap-rr-06-54.ps.gz}, ipdmembership={learning}, }