Spike-timing dependant competitive learning of integrate-and-fire neurons with active dendrites

Christo Panchev; Stefan Wermter; Huixin Chen

doi:10.1007/3-540-46084-5_145

Spike-timing dependant competitive learning of integrate-and-fire neurons with active dendrites

Christo Panchev, Stefan Wermter, Huixin Chen

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

18 Citations (Scopus)

Abstract

Presented is a model of an integrate-and-fire neuron with active dendrites and a spike-timing dependent Hebbian learning rule. The learning algorithm effectively trains the neuron when responding to several types of temporal encoding schemes: temporal code with single spikes, spike bursts and phase coding. The neuron model and learning algorithm are tested on a neural network with a self-organizing map of competitive neurons. The goal of the presented work is to develop computationally efficient models rather than approximating the real neurons. The approach described in this paper demonstrates the potential advantages of using the processing functionalities of active dendrites as a novel paradigm of computing with networks of artificial spiking neurons.

Original language	English
Title of host publication	Artificial Neural Networks — ICANN 2002
Subtitle of host publication	International Conference Madrid, Spain, August 28–30, 2002 Proceedings
Editors	José R. Dorronsoro
Place of Publication	Berlin
Publisher	Springer Verlag
Pages	896-901
Number of pages	6
ISBN (Electronic)	978-3-540-46084-8
ISBN (Print)	978-3-540-44074-1
DOIs	https://doi.org/10.1007/3-540-46084-5_145
Publication status	Published - 2002
Externally published	Yes
Event	International Conference on Artificial Neural Networks - Madrid, Spain Duration: 28 Aug 2002 → 30 Aug 2002

Conference

Conference	International Conference on Artificial Neural Networks
Abbreviated title	ICANN 2002
Country/Territory	Spain
City	Madrid
Period	28/08/02 → 30/08/02

Access to Document

10.1007/3-540-46084-5_145

Cite this

Spike-timing dependant competitive learning of integrate-and-fire neurons with active dendrites. / Panchev, Christo; Wermter, Stefan; Chen, Huixin.

Artificial Neural Networks — ICANN 2002: International Conference Madrid, Spain, August 28–30, 2002 Proceedings. ed. / José R. Dorronsoro. Berlin : Springer Verlag, 2002. p. 896-901.

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Panchev, C, Wermter, S & Chen, H 2002, Spike-timing dependant competitive learning of integrate-and-fire neurons with active dendrites. in JR Dorronsoro (ed.), Artificial Neural Networks — ICANN 2002: International Conference Madrid, Spain, August 28–30, 2002 Proceedings. Springer Verlag, Berlin, pp. 896-901, International Conference on Artificial Neural Networks, Madrid, Spain, 28/08/02. https://doi.org/10.1007/3-540-46084-5_145

@inbook{8b9c01eeed524923a8e3e5b554cfb84d,

title = "Spike-timing dependant competitive learning of integrate-and-fire neurons with active dendrites",

abstract = "Presented is a model of an integrate-and-fire neuron with active dendrites and a spike-timing dependent Hebbian learning rule. The learning algorithm effectively trains the neuron when responding to several types of temporal encoding schemes: temporal code with single spikes, spike bursts and phase coding. The neuron model and learning algorithm are tested on a neural network with a self-organizing map of competitive neurons. The goal of the presented work is to develop computationally efficient models rather than approximating the real neurons. The approach described in this paper demonstrates the potential advantages of using the processing functionalities of active dendrites as a novel paradigm of computing with networks of artificial spiking neurons.",

author = "Christo Panchev and Stefan Wermter and Huixin Chen",

year = "2002",

doi = "10.1007/3-540-46084-5_145",

language = "English",

isbn = "978-3-540-44074-1",

pages = "896--901",

editor = "Dorronsoro, {Jos{\'e} R. }",

booktitle = "Artificial Neural Networks — ICANN 2002",

publisher = "Springer Verlag",

address = "Austria",

note = "International Conference on Artificial Neural Networks, ICANN 2002 ; Conference date: 28-08-2002 Through 30-08-2002",

}

TY - CHAP

T1 - Spike-timing dependant competitive learning of integrate-and-fire neurons with active dendrites

AU - Panchev, Christo

AU - Wermter, Stefan

AU - Chen, Huixin

PY - 2002

Y1 - 2002

N2 - Presented is a model of an integrate-and-fire neuron with active dendrites and a spike-timing dependent Hebbian learning rule. The learning algorithm effectively trains the neuron when responding to several types of temporal encoding schemes: temporal code with single spikes, spike bursts and phase coding. The neuron model and learning algorithm are tested on a neural network with a self-organizing map of competitive neurons. The goal of the presented work is to develop computationally efficient models rather than approximating the real neurons. The approach described in this paper demonstrates the potential advantages of using the processing functionalities of active dendrites as a novel paradigm of computing with networks of artificial spiking neurons.

AB - Presented is a model of an integrate-and-fire neuron with active dendrites and a spike-timing dependent Hebbian learning rule. The learning algorithm effectively trains the neuron when responding to several types of temporal encoding schemes: temporal code with single spikes, spike bursts and phase coding. The neuron model and learning algorithm are tested on a neural network with a self-organizing map of competitive neurons. The goal of the presented work is to develop computationally efficient models rather than approximating the real neurons. The approach described in this paper demonstrates the potential advantages of using the processing functionalities of active dendrites as a novel paradigm of computing with networks of artificial spiking neurons.

U2 - 10.1007/3-540-46084-5_145

DO - 10.1007/3-540-46084-5_145

M3 - Chapter

SN - 978-3-540-44074-1

SP - 896

EP - 901

BT - Artificial Neural Networks — ICANN 2002

A2 - Dorronsoro, José R.

PB - Springer Verlag

CY - Berlin

T2 - International Conference on Artificial Neural Networks

Y2 - 28 August 2002 through 30 August 2002

ER -

Spike-timing dependant competitive learning of integrate-and-fire neurons with active dendrites

Abstract

Conference

Access to Document

Fingerprint

Cite this