A supervised learning approach based on STDP and polychronization in spiking neuron networks. Paugam-Moisy, H., Martinez, R., & Bengio, S. In European Symposium on Artificial Neural Networks, ESANN, 2007. ![A supervised learning approach based on STDP and polychronization in spiking neuron networks [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex 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~i̧teIzh06NComp. The model emphasizes the computational capabilities of this concept.
@inproceedings{paugam:2007:esann,
author = {H. Paugam-Moisy and R. Martinez and S. Bengio},
title = {A supervised learning approach based on {STDP} and polychronization in spiking neuron networks},
booktitle = {European Symposium on Artificial Neural Networks, {ESANN}},
year = 2007,
url = {publications/ps/paugam_2007_esann.ps.gz},
pdf = {publications/pdf/paugam_2007_esann.pdf},
djvu = {publications/djvu/paugam_2007_esann.djvu},
idiap = {publications/pdf/rr06-54.pdf},
original = {2007/spiking_esann},
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.},
categorie = {C},
}
Downloads: 0
{"_id":"sFqK23Hppiv63LM3r","bibbaseid":"paugammoisy-martinez-bengio-asupervisedlearningapproachbasedonstdpandpolychronizationinspikingneuronnetworks-2007","authorIDs":[],"author_short":["Paugam-Moisy, H.","Martinez, R.","Bengio, S."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["H."],"propositions":[],"lastnames":["Paugam-Moisy"],"suffixes":[]},{"firstnames":["R."],"propositions":[],"lastnames":["Martinez"],"suffixes":[]},{"firstnames":["S."],"propositions":[],"lastnames":["Bengio"],"suffixes":[]}],"title":"A supervised learning approach based on STDP and polychronization in spiking neuron networks","booktitle":"European Symposium on Artificial Neural Networks, ESANN","year":"2007","url":"publications/ps/paugam_2007_esann.ps.gz","pdf":"publications/pdf/paugam_2007_esann.pdf","djvu":"publications/djvu/paugam_2007_esann.djvu","idiap":"publications/pdf/rr06-54.pdf","original":"2007/spiking_esann","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~i̧teIzh06NComp. The model emphasizes the computational capabilities of this concept.","categorie":"C","bibtex":"@inproceedings{paugam:2007:esann,\n author = {H. Paugam-Moisy and R. Martinez and S. Bengio},\n title = {A supervised learning approach based on {STDP} and polychronization in spiking neuron networks},\n booktitle = {European Symposium on Artificial Neural Networks, {ESANN}},\n year = 2007,\n url = {publications/ps/paugam_2007_esann.ps.gz},\n pdf = {publications/pdf/paugam_2007_esann.pdf},\n djvu = {publications/djvu/paugam_2007_esann.djvu},\n idiap = {publications/pdf/rr06-54.pdf},\n original = {2007/spiking_esann},\n 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.},\n categorie = {C},\n}\n\n","author_short":["Paugam-Moisy, H.","Martinez, R.","Bengio, S."],"key":"paugam:2007:esann","id":"paugam:2007:esann","bibbaseid":"paugammoisy-martinez-bengio-asupervisedlearningapproachbasedonstdpandpolychronizationinspikingneuronnetworks-2007","role":"author","urls":{"Paper":"http://bengio.abracadoudou.com/publications/ps/paugam_2007_esann.ps.gz"},"downloads":0},"bibtype":"inproceedings","biburl":"http://bengio.abracadoudou.com/samy.bib","creationDate":"2020-03-18T03:43:27.362Z","downloads":0,"keywords":[],"search_terms":["supervised","learning","approach","based","stdp","polychronization","spiking","neuron","networks","paugam-moisy","martinez","bengio"],"title":"A supervised learning approach based on STDP and polychronization in spiking neuron networks","year":2007,"dataSources":["9NCW2CDr4M3s5DvNX"]}