Magnetic Optimization Algorithm for training Multi Layer Perceptron

Seyedali Mirjalili, Ali Safa Sadiq

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

21 Citations (Scopus)

Abstract

Recently, feedforward neural network (FNN), especially Multi Layer Perceptron (MLP) has become one of the most widely-used computational tools, applied to many fields. Back Propagation is the most common method to learn MLP. This learning algorithm is a gradient-based algorithm, but it suffers some drawbacks such as trapping in local minima and slow convergence. These weaknesses make MLP unreliable in solving real-world problems. Using heuristic optimization algorithms is a popular approach to improve the drawbacks of BP. Magnetic Optimization Algorithm (MOA) is a novel heuristic optimization algorithm, inspired from the magnetic field theory. It has been proven that this algorithm is capable of solving optimization problems quickly and accurately. In this paper, MOA is employed as a new training method for MLP in order to improve the aforementioned shortcomings. The proposed learning method was compared with PSO and GA-based learning algorithms using 3-bit XOR and function approximation benchmark problems. The results prove the high performance of this new learning algorithm for large numbers of training samples.

Original languageEnglish
Title of host publication2011 IEEE 3rd International Conference on Communication Software and Networks, ICCSN 2011
Pages42-46
Number of pages5
DOIs
Publication statusPublished - 29 Sep 2011
Externally publishedYes
Event2011 IEEE 3rd International Conference on Communication Software and Networks, ICCSN 2011 - Xi'an, China
Duration: 27 May 201129 May 2011

Publication series

Name2011 IEEE 3rd International Conference on Communication Software and Networks, ICCSN 2011

Conference

Conference2011 IEEE 3rd International Conference on Communication Software and Networks, ICCSN 2011
CountryChina
CityXi'an
Period27/05/1129/05/11

Keywords

  • Back Propagation algorithm
  • BP
  • Magnetic Optimization Algorithm
  • MLP
  • MOA
  • Multi layer perceptron

Fingerprint Dive into the research topics of 'Magnetic Optimization Algorithm for training Multi Layer Perceptron'. Together they form a unique fingerprint.

  • Cite this

    Mirjalili, S., & Sadiq, A. S. (2011). Magnetic Optimization Algorithm for training Multi Layer Perceptron. In 2011 IEEE 3rd International Conference on Communication Software and Networks, ICCSN 2011 (pp. 42-46). [6014845] (2011 IEEE 3rd International Conference on Communication Software and Networks, ICCSN 2011). https://doi.org/10.1109/ICCSN.2011.6014845