An adaptive spiking neural network with Hebbian learning

Lyle Norman Long

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

2 Citations (Scopus)

Abstract

This paper will describe a numerical approach to simulating biologically-plausible spiking neural networks. These are time dependent neural networks with realistic models for the neurons (Hodgkin-Huxley). In addition the learning is biologically plausible as well, being a Hebbian approach based on spike timing dependent plasticity (STDP). To make the approach very general and flexible, neurogenesis and synaptogenesis have been implemented, which allows the code to automatically add or remove neurons (or synapses) as required.

Original languageEnglish (US)
Title of host publicationIEEE SSCI 2011
Subtitle of host publicationSymposium Series on Computational Intelligence - EAIS 2011: 2011 IEEE Workshop on Evolving and Adaptive Intelligent Systems
Pages17-23
Number of pages7
DOIs
StatePublished - Aug 15 2011
EventSymposium Series on Computational Intelligence, IEEE SSCI 2011 - 2011 IEEE 5th Workshop on Evolving and Adaptive Intelligent Systems, EAIS 2011 - Paris, France
Duration: Apr 11 2011Apr 15 2011

Other

OtherSymposium Series on Computational Intelligence, IEEE SSCI 2011 - 2011 IEEE 5th Workshop on Evolving and Adaptive Intelligent Systems, EAIS 2011
CountryFrance
CityParis
Period4/11/114/15/11

Fingerprint

Neurons
Neural networks
Plasticity

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Information Systems
  • Control and Systems Engineering

Cite this

Long, L. N. (2011). An adaptive spiking neural network with Hebbian learning. In IEEE SSCI 2011: Symposium Series on Computational Intelligence - EAIS 2011: 2011 IEEE Workshop on Evolving and Adaptive Intelligent Systems (pp. 17-23). [5945923] https://doi.org/10.1109/EAIS.2011.5945923
Long, Lyle Norman. / An adaptive spiking neural network with Hebbian learning. IEEE SSCI 2011: Symposium Series on Computational Intelligence - EAIS 2011: 2011 IEEE Workshop on Evolving and Adaptive Intelligent Systems. 2011. pp. 17-23
@inproceedings{c2fe939c252c42d69537d0bde9e0068f,
title = "An adaptive spiking neural network with Hebbian learning",
abstract = "This paper will describe a numerical approach to simulating biologically-plausible spiking neural networks. These are time dependent neural networks with realistic models for the neurons (Hodgkin-Huxley). In addition the learning is biologically plausible as well, being a Hebbian approach based on spike timing dependent plasticity (STDP). To make the approach very general and flexible, neurogenesis and synaptogenesis have been implemented, which allows the code to automatically add or remove neurons (or synapses) as required.",
author = "Long, {Lyle Norman}",
year = "2011",
month = "8",
day = "15",
doi = "10.1109/EAIS.2011.5945923",
language = "English (US)",
isbn = "9781424499793",
pages = "17--23",
booktitle = "IEEE SSCI 2011",

}

Long, LN 2011, An adaptive spiking neural network with Hebbian learning. in IEEE SSCI 2011: Symposium Series on Computational Intelligence - EAIS 2011: 2011 IEEE Workshop on Evolving and Adaptive Intelligent Systems., 5945923, pp. 17-23, Symposium Series on Computational Intelligence, IEEE SSCI 2011 - 2011 IEEE 5th Workshop on Evolving and Adaptive Intelligent Systems, EAIS 2011, Paris, France, 4/11/11. https://doi.org/10.1109/EAIS.2011.5945923

An adaptive spiking neural network with Hebbian learning. / Long, Lyle Norman.

IEEE SSCI 2011: Symposium Series on Computational Intelligence - EAIS 2011: 2011 IEEE Workshop on Evolving and Adaptive Intelligent Systems. 2011. p. 17-23 5945923.

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

TY - GEN

T1 - An adaptive spiking neural network with Hebbian learning

AU - Long, Lyle Norman

PY - 2011/8/15

Y1 - 2011/8/15

N2 - This paper will describe a numerical approach to simulating biologically-plausible spiking neural networks. These are time dependent neural networks with realistic models for the neurons (Hodgkin-Huxley). In addition the learning is biologically plausible as well, being a Hebbian approach based on spike timing dependent plasticity (STDP). To make the approach very general and flexible, neurogenesis and synaptogenesis have been implemented, which allows the code to automatically add or remove neurons (or synapses) as required.

AB - This paper will describe a numerical approach to simulating biologically-plausible spiking neural networks. These are time dependent neural networks with realistic models for the neurons (Hodgkin-Huxley). In addition the learning is biologically plausible as well, being a Hebbian approach based on spike timing dependent plasticity (STDP). To make the approach very general and flexible, neurogenesis and synaptogenesis have been implemented, which allows the code to automatically add or remove neurons (or synapses) as required.

UR - http://www.scopus.com/inward/record.url?scp=80051524296&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051524296&partnerID=8YFLogxK

U2 - 10.1109/EAIS.2011.5945923

DO - 10.1109/EAIS.2011.5945923

M3 - Conference contribution

AN - SCOPUS:80051524296

SN - 9781424499793

SP - 17

EP - 23

BT - IEEE SSCI 2011

ER -

Long LN. An adaptive spiking neural network with Hebbian learning. In IEEE SSCI 2011: Symposium Series on Computational Intelligence - EAIS 2011: 2011 IEEE Workshop on Evolving and Adaptive Intelligent Systems. 2011. p. 17-23. 5945923 https://doi.org/10.1109/EAIS.2011.5945923