Multi-DL-ReSuMe: Multiple neurons Delay Learning Remote Supervised Method

Aboozar Taherkhani, Ammar Belatreche, Yuhua Li, Liam Maguire

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

5 Citations (Scopus)

Abstract

Spikes are an important part of information transmission between neurons in the biological brain. Biological evidence shows that information is carried in the timing of individual action potentials, rather than only the firing rate. Spiking neural networks are devised to capture more biological characteristics of the brain to construct more powerful intelligent systems. In this paper, we extend our newly proposed supervised learning algorithm called DL-ReSuMe (Delay Learning Remote Supervised Method) to train multiple neurons to classify spatiotemporal spiking patterns. In this method, a number of neurons instead of a single neuron is trained to perform the classification task. The simulation results show that a population of neurons has significantly higher processing ability compared to a single neuron. It is also shown that the performance of Multi-DL-ReSuMe (Multiple DL-ReSuMe) is increased when the number of desired spikes is increased in the desired spike trains to an appropriate number.
LanguageEnglish
Title of host publicationUnknown Host Publication
Number of pages7
DOIs
Publication statusPublished - Jul 2015
EventInternational Joint Conference on Neural Networks (IJCNN) - Ireland
Duration: 1 Jul 2015 → …

Conference

ConferenceInternational Joint Conference on Neural Networks (IJCNN)
Period1/07/15 → …

Fingerprint

Neurons
Brain
Supervised learning
Intelligent systems
Learning algorithms
Neural networks
Processing

Keywords

  • classification
  • delay learning
  • spatiotemporal patterns
  • spiking neural network
  • supervised learning

Cite this

Taherkhani, Aboozar ; Belatreche, Ammar ; Li, Yuhua ; Maguire, Liam. / Multi-DL-ReSuMe: Multiple neurons Delay Learning Remote Supervised Method. Unknown Host Publication. 2015.
@inproceedings{3f599d20dc414bb99b7e312b43bae657,
title = "Multi-DL-ReSuMe: Multiple neurons Delay Learning Remote Supervised Method",
abstract = "Spikes are an important part of information transmission between neurons in the biological brain. Biological evidence shows that information is carried in the timing of individual action potentials, rather than only the firing rate. Spiking neural networks are devised to capture more biological characteristics of the brain to construct more powerful intelligent systems. In this paper, we extend our newly proposed supervised learning algorithm called DL-ReSuMe (Delay Learning Remote Supervised Method) to train multiple neurons to classify spatiotemporal spiking patterns. In this method, a number of neurons instead of a single neuron is trained to perform the classification task. The simulation results show that a population of neurons has significantly higher processing ability compared to a single neuron. It is also shown that the performance of Multi-DL-ReSuMe (Multiple DL-ReSuMe) is increased when the number of desired spikes is increased in the desired spike trains to an appropriate number.",
keywords = "classification, delay learning, spatiotemporal patterns, spiking neural network, supervised learning",
author = "Aboozar Taherkhani and Ammar Belatreche and Yuhua Li and Liam Maguire",
year = "2015",
month = "7",
doi = "10.1109/IJCNN.2015.7280743",
language = "English",
booktitle = "Unknown Host Publication",

}

Taherkhani, A, Belatreche, A, Li, Y & Maguire, L 2015, Multi-DL-ReSuMe: Multiple neurons Delay Learning Remote Supervised Method. in Unknown Host Publication. International Joint Conference on Neural Networks (IJCNN), 1/07/15. https://doi.org/10.1109/IJCNN.2015.7280743

Multi-DL-ReSuMe: Multiple neurons Delay Learning Remote Supervised Method. / Taherkhani, Aboozar; Belatreche, Ammar; Li, Yuhua; Maguire, Liam.

Unknown Host Publication. 2015.

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

TY - GEN

T1 - Multi-DL-ReSuMe: Multiple neurons Delay Learning Remote Supervised Method

AU - Taherkhani, Aboozar

AU - Belatreche, Ammar

AU - Li, Yuhua

AU - Maguire, Liam

PY - 2015/7

Y1 - 2015/7

N2 - Spikes are an important part of information transmission between neurons in the biological brain. Biological evidence shows that information is carried in the timing of individual action potentials, rather than only the firing rate. Spiking neural networks are devised to capture more biological characteristics of the brain to construct more powerful intelligent systems. In this paper, we extend our newly proposed supervised learning algorithm called DL-ReSuMe (Delay Learning Remote Supervised Method) to train multiple neurons to classify spatiotemporal spiking patterns. In this method, a number of neurons instead of a single neuron is trained to perform the classification task. The simulation results show that a population of neurons has significantly higher processing ability compared to a single neuron. It is also shown that the performance of Multi-DL-ReSuMe (Multiple DL-ReSuMe) is increased when the number of desired spikes is increased in the desired spike trains to an appropriate number.

AB - Spikes are an important part of information transmission between neurons in the biological brain. Biological evidence shows that information is carried in the timing of individual action potentials, rather than only the firing rate. Spiking neural networks are devised to capture more biological characteristics of the brain to construct more powerful intelligent systems. In this paper, we extend our newly proposed supervised learning algorithm called DL-ReSuMe (Delay Learning Remote Supervised Method) to train multiple neurons to classify spatiotemporal spiking patterns. In this method, a number of neurons instead of a single neuron is trained to perform the classification task. The simulation results show that a population of neurons has significantly higher processing ability compared to a single neuron. It is also shown that the performance of Multi-DL-ReSuMe (Multiple DL-ReSuMe) is increased when the number of desired spikes is increased in the desired spike trains to an appropriate number.

KW - classification

KW - delay learning

KW - spatiotemporal patterns

KW - spiking neural network

KW - supervised learning

U2 - 10.1109/IJCNN.2015.7280743

DO - 10.1109/IJCNN.2015.7280743

M3 - Conference contribution

BT - Unknown Host Publication

ER -