A Review Of Learning In Biologically Plausible Spiking Neural Networks

Aboozar Taherkhani, Ammar Belatreche, Yuhua Li, Georgina Cosma, Liam Maguire, T.Martin McGinnity

Research output: Contribution to journalArticle

Abstract

Artificial neural networks have been used as a powerful processing tool in various areas such as pattern recognition, control, robotics, and bioinformatics. Their wide applicability has encouraged researchers to improve artificial neural networks by investigating the biological brain. Neurological research has significantly progressed in recent years and continues to reveal new characteristics of biological neurons. New technologies can now capture temporal changes in the internal activity of the brain in more detail and help clarify the relationship between brain activity and the perception of a given stimulus. This new knowledge has led to a new type of artificial neural network, the Spiking Neural Network (SNN), that draws more faithfully on biological properties to provide higher processing abilities. A review of recent developments in learning of spiking neurons is presented in this paper. First the biological background of SNN learning algorithms is reviewed. The important elements of a learning algorithm such as the neuron model, synaptic plasticity, information encoding and SNN topologies are then presented. Then, a critical review of the state-of-the-art learning algorithms for SNNs using single and multiple spikes is presented. Additionally, deep spiking neural networks are reviewed, and challenges and opportunities in the SNN field are discussed.
LanguageEnglish
Pages253-272
Number of pages20
JournalNeural Networks
Volume122
Early online date11 Oct 2019
DOIs
Publication statusE-pub ahead of print - 11 Oct 2019

Fingerprint

Learning
Neural networks
Neurons
Brain
Learning algorithms
Neuronal Plasticity
Aptitude
Robotics
Computational Biology
Research Personnel
Technology
Bioinformatics
Processing
Pattern recognition
Plasticity
Research
Topology
Recognition (Psychology)

Keywords

  • Neural networks
  • biological learning
  • spiking
  • Learning
  • Spiking neural network (SNN)
  • Synaptic plasticity

Cite this

Taherkhani, Aboozar ; Belatreche, Ammar ; Li, Yuhua ; Cosma, Georgina ; Maguire, Liam ; McGinnity, T.Martin. / A Review Of Learning In Biologically Plausible Spiking Neural Networks. In: Neural Networks. 2019 ; Vol. 122. pp. 253-272.
@article{ae08b96c0d7f4c05a6e34c287ad0beea,
title = "A Review Of Learning In Biologically Plausible Spiking Neural Networks",
abstract = "Artificial neural networks have been used as a powerful processing tool in various areas such as pattern recognition, control, robotics, and bioinformatics. Their wide applicability has encouraged researchers to improve artificial neural networks by investigating the biological brain. Neurological research has significantly progressed in recent years and continues to reveal new characteristics of biological neurons. New technologies can now capture temporal changes in the internal activity of the brain in more detail and help clarify the relationship between brain activity and the perception of a given stimulus. This new knowledge has led to a new type of artificial neural network, the Spiking Neural Network (SNN), that draws more faithfully on biological properties to provide higher processing abilities. A review of recent developments in learning of spiking neurons is presented in this paper. First the biological background of SNN learning algorithms is reviewed. The important elements of a learning algorithm such as the neuron model, synaptic plasticity, information encoding and SNN topologies are then presented. Then, a critical review of the state-of-the-art learning algorithms for SNNs using single and multiple spikes is presented. Additionally, deep spiking neural networks are reviewed, and challenges and opportunities in the SNN field are discussed.",
keywords = "Neural networks, biological learning, spiking, Learning, Spiking neural network (SNN), Synaptic plasticity",
author = "Aboozar Taherkhani and Ammar Belatreche and Yuhua Li and Georgina Cosma and Liam Maguire and T.Martin McGinnity",
year = "2019",
month = "10",
day = "11",
doi = "10.1016/j.neunet.2019.09.036",
language = "English",
volume = "122",
pages = "253--272",
journal = "Neural Networks",
issn = "0893-6080",
publisher = "Elsevier",

}

A Review Of Learning In Biologically Plausible Spiking Neural Networks. / Taherkhani, Aboozar; Belatreche, Ammar; Li, Yuhua; Cosma, Georgina; Maguire, Liam; McGinnity, T.Martin.

In: Neural Networks, Vol. 122, 11.10.2019, p. 253-272.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Review Of Learning In Biologically Plausible Spiking Neural Networks

AU - Taherkhani, Aboozar

AU - Belatreche, Ammar

AU - Li, Yuhua

AU - Cosma, Georgina

AU - Maguire, Liam

AU - McGinnity, T.Martin

PY - 2019/10/11

Y1 - 2019/10/11

N2 - Artificial neural networks have been used as a powerful processing tool in various areas such as pattern recognition, control, robotics, and bioinformatics. Their wide applicability has encouraged researchers to improve artificial neural networks by investigating the biological brain. Neurological research has significantly progressed in recent years and continues to reveal new characteristics of biological neurons. New technologies can now capture temporal changes in the internal activity of the brain in more detail and help clarify the relationship between brain activity and the perception of a given stimulus. This new knowledge has led to a new type of artificial neural network, the Spiking Neural Network (SNN), that draws more faithfully on biological properties to provide higher processing abilities. A review of recent developments in learning of spiking neurons is presented in this paper. First the biological background of SNN learning algorithms is reviewed. The important elements of a learning algorithm such as the neuron model, synaptic plasticity, information encoding and SNN topologies are then presented. Then, a critical review of the state-of-the-art learning algorithms for SNNs using single and multiple spikes is presented. Additionally, deep spiking neural networks are reviewed, and challenges and opportunities in the SNN field are discussed.

AB - Artificial neural networks have been used as a powerful processing tool in various areas such as pattern recognition, control, robotics, and bioinformatics. Their wide applicability has encouraged researchers to improve artificial neural networks by investigating the biological brain. Neurological research has significantly progressed in recent years and continues to reveal new characteristics of biological neurons. New technologies can now capture temporal changes in the internal activity of the brain in more detail and help clarify the relationship between brain activity and the perception of a given stimulus. This new knowledge has led to a new type of artificial neural network, the Spiking Neural Network (SNN), that draws more faithfully on biological properties to provide higher processing abilities. A review of recent developments in learning of spiking neurons is presented in this paper. First the biological background of SNN learning algorithms is reviewed. The important elements of a learning algorithm such as the neuron model, synaptic plasticity, information encoding and SNN topologies are then presented. Then, a critical review of the state-of-the-art learning algorithms for SNNs using single and multiple spikes is presented. Additionally, deep spiking neural networks are reviewed, and challenges and opportunities in the SNN field are discussed.

KW - Neural networks

KW - biological learning

KW - spiking

KW - Learning

KW - Spiking neural network (SNN)

KW - Synaptic plasticity

UR - http://www.scopus.com/inward/record.url?scp=85074802056&partnerID=8YFLogxK

U2 - 10.1016/j.neunet.2019.09.036

DO - 10.1016/j.neunet.2019.09.036

M3 - Article

VL - 122

SP - 253

EP - 272

JO - Neural Networks

T2 - Neural Networks

JF - Neural Networks

SN - 0893-6080

ER -