Artificial bee colony training of neural networks

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)peer-review

Standard

Artificial bee colony training of neural networks. / Bullinaria, John; Alyahya, Khulood.

Nature Inspired Cooperative Strategies for Optimization (NICSO 2013): learning, optimization and interdisciplinary applications. ed. / German Terrazas; Fernando E. B. Otero; Antonio D. Masegosa. Springer, 2014. p. 191-201.

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)peer-review

Harvard

Bullinaria, J & Alyahya, K 2014, Artificial bee colony training of neural networks. in G Terrazas, FEB Otero & AD Masegosa (eds), Nature Inspired Cooperative Strategies for Optimization (NICSO 2013): learning, optimization and interdisciplinary applications. Springer, pp. 191-201, Nature Inspired Cooperative Strategies for Optimization (NICSO 2013), United Kingdom, 2/09/13. <http://www.springer.com/gp/book/9783319016917>

APA

Bullinaria, J., & Alyahya, K. (2014). Artificial bee colony training of neural networks. In G. Terrazas, F. E. B. Otero, & A. D. Masegosa (Eds.), Nature Inspired Cooperative Strategies for Optimization (NICSO 2013): learning, optimization and interdisciplinary applications (pp. 191-201). Springer. http://www.springer.com/gp/book/9783319016917

Vancouver

Bullinaria J, Alyahya K. Artificial bee colony training of neural networks. In Terrazas G, Otero FEB, Masegosa AD, editors, Nature Inspired Cooperative Strategies for Optimization (NICSO 2013): learning, optimization and interdisciplinary applications. Springer. 2014. p. 191-201

Author

Bullinaria, John ; Alyahya, Khulood. / Artificial bee colony training of neural networks. Nature Inspired Cooperative Strategies for Optimization (NICSO 2013): learning, optimization and interdisciplinary applications. editor / German Terrazas ; Fernando E. B. Otero ; Antonio D. Masegosa. Springer, 2014. pp. 191-201

Bibtex

@inbook{99da5fa2b350471ab1fe47ba4a911175,
title = "Artificial bee colony training of neural networks",
abstract = "The Artificial Bee Colony (ABC) is a recently introduced swarm intelligence algorithm for optimization that has previously been applied successfully to the training of neural networks. This paper explores more carefully the performance of the ABC algorithm for optimizing the connection weights of feed-forward neural networks for classification tasks, and presents a more rigorous comparison with the traditional Back-Propagation (BP) training algorithm. The empirical results show that using the standard \stopping early{"} approach with optimized learning parameters leads to improved BP performance over the previous comparative study, and that a simple variation of the ABC approach provides improved ABC performance too. With both improvements applied, we conclude that the ABC approach does perform very well on small problems, but the generalization performances achieved are only significantly better than standard BP on one out of six datasets, and the training times increase rapidly as the size of the problem grows. ",
author = "John Bullinaria and Khulood Alyahya",
year = "2014",
language = "English",
isbn = "9783319016917",
pages = "191--201",
editor = "{ Terrazas}, German and Otero, {Fernando E. B.} and Masegosa, {Antonio D.}",
booktitle = "Nature Inspired Cooperative Strategies for Optimization (NICSO 2013)",
publisher = "Springer",
note = "Nature Inspired Cooperative Strategies for Optimization (NICSO 2013) ; Conference date: 02-09-2013",

}

RIS

TY - CHAP

T1 - Artificial bee colony training of neural networks

AU - Bullinaria, John

AU - Alyahya, Khulood

PY - 2014

Y1 - 2014

N2 - The Artificial Bee Colony (ABC) is a recently introduced swarm intelligence algorithm for optimization that has previously been applied successfully to the training of neural networks. This paper explores more carefully the performance of the ABC algorithm for optimizing the connection weights of feed-forward neural networks for classification tasks, and presents a more rigorous comparison with the traditional Back-Propagation (BP) training algorithm. The empirical results show that using the standard \stopping early" approach with optimized learning parameters leads to improved BP performance over the previous comparative study, and that a simple variation of the ABC approach provides improved ABC performance too. With both improvements applied, we conclude that the ABC approach does perform very well on small problems, but the generalization performances achieved are only significantly better than standard BP on one out of six datasets, and the training times increase rapidly as the size of the problem grows.

AB - The Artificial Bee Colony (ABC) is a recently introduced swarm intelligence algorithm for optimization that has previously been applied successfully to the training of neural networks. This paper explores more carefully the performance of the ABC algorithm for optimizing the connection weights of feed-forward neural networks for classification tasks, and presents a more rigorous comparison with the traditional Back-Propagation (BP) training algorithm. The empirical results show that using the standard \stopping early" approach with optimized learning parameters leads to improved BP performance over the previous comparative study, and that a simple variation of the ABC approach provides improved ABC performance too. With both improvements applied, we conclude that the ABC approach does perform very well on small problems, but the generalization performances achieved are only significantly better than standard BP on one out of six datasets, and the training times increase rapidly as the size of the problem grows.

M3 - Chapter (peer-reviewed)

SN - 9783319016917

SP - 191

EP - 201

BT - Nature Inspired Cooperative Strategies for Optimization (NICSO 2013)

A2 - Terrazas, German

A2 - Otero, Fernando E. B.

A2 - Masegosa, Antonio D.

PB - Springer

T2 - Nature Inspired Cooperative Strategies for Optimization (NICSO 2013)

Y2 - 2 September 2013

ER -