Home > Research > Publications & Outputs > Spiking neural network training using evolution...
View graph of relations

Spiking neural network training using evolutionary algorithms

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Spiking neural network training using evolutionary algorithms. / Pavlidis, Nicos; Tasoulis, DK; Plagianakos, Vassilis P. et al.
International Joint Conference on Neural Networks (IJCNN 2005). Vol. 4 IEEE, 2005. p. 2190-2194.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Pavlidis, N, Tasoulis, DK, Plagianakos, VP, Vrahatis, MN & Nikiforidis, G 2005, Spiking neural network training using evolutionary algorithms. in International Joint Conference on Neural Networks (IJCNN 2005). vol. 4, IEEE, pp. 2190-2194. https://doi.org/10.1109/IJCNN.2005.1556240

APA

Pavlidis, N., Tasoulis, DK., Plagianakos, V. P., Vrahatis, M. N., & Nikiforidis, G. (2005). Spiking neural network training using evolutionary algorithms. In International Joint Conference on Neural Networks (IJCNN 2005) (Vol. 4, pp. 2190-2194). IEEE. https://doi.org/10.1109/IJCNN.2005.1556240

Vancouver

Pavlidis N, Tasoulis DK, Plagianakos VP, Vrahatis MN, Nikiforidis G. Spiking neural network training using evolutionary algorithms. In International Joint Conference on Neural Networks (IJCNN 2005). Vol. 4. IEEE. 2005. p. 2190-2194 doi: 10.1109/IJCNN.2005.1556240

Author

Pavlidis, Nicos ; Tasoulis, DK ; Plagianakos, Vassilis P. et al. / Spiking neural network training using evolutionary algorithms. International Joint Conference on Neural Networks (IJCNN 2005). Vol. 4 IEEE, 2005. pp. 2190-2194

Bibtex

@inproceedings{975b2949362f4bc1bee191b047f0d960,
title = "Spiking neural network training using evolutionary algorithms",
abstract = "Networks of spiking neurons can perform complex non-linear computations in fast temporal coding just as well as rate coded networks. These networks differ from previous models in that spiking neurons communicate information by the timing, rather than the rate, of spikes. To apply spiking neural networks on particular tasks, a learning process is required. Most existing training algorithms are based on unsupervised Hebbian learning. In this paper, we investigate the performance of the parallel differential evolution algorithm, as a supervised training algorithm for spiking neural networks. The approach was successfully tested on well-known and widely used classification problems.",
author = "Nicos Pavlidis and DK Tasoulis and Plagianakos, {Vassilis P.} and Vrahatis, {Michael N.} and G. Nikiforidis",
year = "2005",
doi = "10.1109/IJCNN.2005.1556240",
language = "English",
isbn = "0-7803-9048-2 ",
volume = "4",
pages = "2190--2194",
booktitle = "International Joint Conference on Neural Networks (IJCNN 2005)",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Spiking neural network training using evolutionary algorithms

AU - Pavlidis, Nicos

AU - Tasoulis, DK

AU - Plagianakos, Vassilis P.

AU - Vrahatis, Michael N.

AU - Nikiforidis, G.

PY - 2005

Y1 - 2005

N2 - Networks of spiking neurons can perform complex non-linear computations in fast temporal coding just as well as rate coded networks. These networks differ from previous models in that spiking neurons communicate information by the timing, rather than the rate, of spikes. To apply spiking neural networks on particular tasks, a learning process is required. Most existing training algorithms are based on unsupervised Hebbian learning. In this paper, we investigate the performance of the parallel differential evolution algorithm, as a supervised training algorithm for spiking neural networks. The approach was successfully tested on well-known and widely used classification problems.

AB - Networks of spiking neurons can perform complex non-linear computations in fast temporal coding just as well as rate coded networks. These networks differ from previous models in that spiking neurons communicate information by the timing, rather than the rate, of spikes. To apply spiking neural networks on particular tasks, a learning process is required. Most existing training algorithms are based on unsupervised Hebbian learning. In this paper, we investigate the performance of the parallel differential evolution algorithm, as a supervised training algorithm for spiking neural networks. The approach was successfully tested on well-known and widely used classification problems.

U2 - 10.1109/IJCNN.2005.1556240

DO - 10.1109/IJCNN.2005.1556240

M3 - Conference contribution/Paper

SN - 0-7803-9048-2

VL - 4

SP - 2190

EP - 2194

BT - International Joint Conference on Neural Networks (IJCNN 2005)

PB - IEEE

ER -