### Abstract

Electromagnetic algorithm is a population based meta-heuristic which imitates the attraction and repulsion of sample points. In this paper, we propose an electromagnetic algorithm to simultaneously tune the structure and parameter of the feed forward neural network. Each solution in the electromagnetic algorithm contains both the design structure and the parameters values of the neural network. This solution later will be used by the neural network to represents its configuration. The classification accuracy returned by the neural network represents the quality of the solution. The performance of the proposed method is verified by using the well-known classification benchmarks and compared against the latest methodologies in the literature. Empirical results demonstrate that the proposed algorithm is able to obtain competitive results, when compared to the best-known results in the literature.

Original language | English |
---|---|

Title of host publication | Proceedings of the 2014 IEEE Congress on Evolutionary Computation, CEC 2014 |

Publisher | Institute of Electrical and Electronics Engineers Inc. |

Pages | 326-331 |

Number of pages | 6 |

ISBN (Print) | 9781479914883 |

DOIs | |

Publication status | Published - 16 Sep 2014 |

Event | 2014 IEEE Congress on Evolutionary Computation, CEC 2014 - Beijing Duration: 6 Jul 2014 → 11 Jul 2014 |

### Other

Other | 2014 IEEE Congress on Evolutionary Computation, CEC 2014 |
---|---|

City | Beijing |

Period | 6/7/14 → 11/7/14 |

### Fingerprint

### ASJC Scopus subject areas

- Artificial Intelligence
- Computational Theory and Mathematics
- Theoretical Computer Science

### Cite this

*Proceedings of the 2014 IEEE Congress on Evolutionary Computation, CEC 2014*(pp. 326-331). [6900291] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CEC.2014.6900291

**Electromagnetic algorithm for tuning the structure and parameters of neural networks.** / Turky, Ayad Mashaan; Abdullah, Salwani; Sabar, Nasser R.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*Proceedings of the 2014 IEEE Congress on Evolutionary Computation, CEC 2014.*, 6900291, Institute of Electrical and Electronics Engineers Inc., pp. 326-331, 2014 IEEE Congress on Evolutionary Computation, CEC 2014, Beijing, 6/7/14. https://doi.org/10.1109/CEC.2014.6900291

}

TY - GEN

T1 - Electromagnetic algorithm for tuning the structure and parameters of neural networks

AU - Turky, Ayad Mashaan

AU - Abdullah, Salwani

AU - Sabar, Nasser R.

PY - 2014/9/16

Y1 - 2014/9/16

N2 - Electromagnetic algorithm is a population based meta-heuristic which imitates the attraction and repulsion of sample points. In this paper, we propose an electromagnetic algorithm to simultaneously tune the structure and parameter of the feed forward neural network. Each solution in the electromagnetic algorithm contains both the design structure and the parameters values of the neural network. This solution later will be used by the neural network to represents its configuration. The classification accuracy returned by the neural network represents the quality of the solution. The performance of the proposed method is verified by using the well-known classification benchmarks and compared against the latest methodologies in the literature. Empirical results demonstrate that the proposed algorithm is able to obtain competitive results, when compared to the best-known results in the literature.

AB - Electromagnetic algorithm is a population based meta-heuristic which imitates the attraction and repulsion of sample points. In this paper, we propose an electromagnetic algorithm to simultaneously tune the structure and parameter of the feed forward neural network. Each solution in the electromagnetic algorithm contains both the design structure and the parameters values of the neural network. This solution later will be used by the neural network to represents its configuration. The classification accuracy returned by the neural network represents the quality of the solution. The performance of the proposed method is verified by using the well-known classification benchmarks and compared against the latest methodologies in the literature. Empirical results demonstrate that the proposed algorithm is able to obtain competitive results, when compared to the best-known results in the literature.

UR - http://www.scopus.com/inward/record.url?scp=84908577767&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908577767&partnerID=8YFLogxK

U2 - 10.1109/CEC.2014.6900291

DO - 10.1109/CEC.2014.6900291

M3 - Conference contribution

AN - SCOPUS:84908577767

SN - 9781479914883

SP - 326

EP - 331

BT - Proceedings of the 2014 IEEE Congress on Evolutionary Computation, CEC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -