A new biologically plausible supervised learning method for spiking neurons

Aboozar Taherkhani, Ammar Belatreche, Yuhua Li, Liam Maguire

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

STDP is believed to play an important role in learning and memory. Additionally, experimental evidence shows that a few strong neural inputs can drive a neuron response and subsequently affect the learning of other inputs. Furthermore, recent studies have shown that local dendritic depolarization canimpact STDP induction. This paper integrates these three biological concepts to devise a new biologically plausible supervised learning method for spiking neurons. Experimental results show that the proposed method can effectively map a random spatiotemporal input pattern to a random target output spike train with a much faster learning speed than ReSuMe.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages11-16
Number of pages6
Publication statusPublished - 17 Mar 2014
Event22st European Symposium on Artificial Neural Networks, Computational Intelligence And Machine Learning - Bruges, Belgium
Duration: 17 Mar 2014 → …

Conference

Conference22st European Symposium on Artificial Neural Networks, Computational Intelligence And Machine Learning
Period17/03/14 → …

Fingerprint

Supervised learning
Neurons
Depolarization
Data storage equipment

Cite this

Taherkhani, A., Belatreche, A., Li, Y., & Maguire, L. (2014). A new biologically plausible supervised learning method for spiking neurons. In Unknown Host Publication (pp. 11-16)
Taherkhani, Aboozar ; Belatreche, Ammar ; Li, Yuhua ; Maguire, Liam. / A new biologically plausible supervised learning method for spiking neurons. Unknown Host Publication. 2014. pp. 11-16
@inproceedings{3cf7366f2e074ee39623af78524cb59e,
title = "A new biologically plausible supervised learning method for spiking neurons",
abstract = "STDP is believed to play an important role in learning and memory. Additionally, experimental evidence shows that a few strong neural inputs can drive a neuron response and subsequently affect the learning of other inputs. Furthermore, recent studies have shown that local dendritic depolarization canimpact STDP induction. This paper integrates these three biological concepts to devise a new biologically plausible supervised learning method for spiking neurons. Experimental results show that the proposed method can effectively map a random spatiotemporal input pattern to a random target output spike train with a much faster learning speed than ReSuMe.",
author = "Aboozar Taherkhani and Ammar Belatreche and Yuhua Li and Liam Maguire",
year = "2014",
month = "3",
day = "17",
language = "English",
isbn = "ISBN 978-287419095-7",
pages = "11--16",
booktitle = "Unknown Host Publication",

}

Taherkhani, A, Belatreche, A, Li, Y & Maguire, L 2014, A new biologically plausible supervised learning method for spiking neurons. in Unknown Host Publication. pp. 11-16, 22st European Symposium on Artificial Neural Networks, Computational Intelligence And Machine Learning, 17/03/14.

A new biologically plausible supervised learning method for spiking neurons. / Taherkhani, Aboozar; Belatreche, Ammar; Li, Yuhua; Maguire, Liam.

Unknown Host Publication. 2014. p. 11-16.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A new biologically plausible supervised learning method for spiking neurons

AU - Taherkhani, Aboozar

AU - Belatreche, Ammar

AU - Li, Yuhua

AU - Maguire, Liam

PY - 2014/3/17

Y1 - 2014/3/17

N2 - STDP is believed to play an important role in learning and memory. Additionally, experimental evidence shows that a few strong neural inputs can drive a neuron response and subsequently affect the learning of other inputs. Furthermore, recent studies have shown that local dendritic depolarization canimpact STDP induction. This paper integrates these three biological concepts to devise a new biologically plausible supervised learning method for spiking neurons. Experimental results show that the proposed method can effectively map a random spatiotemporal input pattern to a random target output spike train with a much faster learning speed than ReSuMe.

AB - STDP is believed to play an important role in learning and memory. Additionally, experimental evidence shows that a few strong neural inputs can drive a neuron response and subsequently affect the learning of other inputs. Furthermore, recent studies have shown that local dendritic depolarization canimpact STDP induction. This paper integrates these three biological concepts to devise a new biologically plausible supervised learning method for spiking neurons. Experimental results show that the proposed method can effectively map a random spatiotemporal input pattern to a random target output spike train with a much faster learning speed than ReSuMe.

M3 - Conference contribution

SN - ISBN 978-287419095-7

SP - 11

EP - 16

BT - Unknown Host Publication

ER -

Taherkhani A, Belatreche A, Li Y, Maguire L. A new biologically plausible supervised learning method for spiking neurons. In Unknown Host Publication. 2014. p. 11-16