Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

A study on performance of MHDA in training MLPs

A study on performance of MHDA in training MLPs In recent years, the application of metaheuristics in training neural network models has gained significance due to the drawbacks of deterministic algorithms. This paper aims to propose the use of a recently developed “memory based hybrid dragonfly algorithm” (MHDA) for training multi-layer perceptron (MLP) model by finding the optimal set of weight and biases.Design/methodology/approachThe efficiency of MHDA in training MLPs is evaluated by applying it to classification and approximation benchmark data sets. Performance comparison between MHDA and other training algorithms is carried out and the significance of results is proved by statistical methods. The computational complexity of MHDA trained MLP is estimated.FindingsSimulation result shows that MHDA can effectively find the near optimum set of weight and biases at a higher convergence rate when compared to other training algorithms.Originality/valueThis paper presents MHDA as an alternative optimization algorithm for training MLP. MHDA can effectively optimize set of weight and biases and can be a potential trainer for MLPs. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Engineering Computations Emerald Publishing

A study on performance of MHDA in training MLPs

K.S., Sree Ranjini
Engineering Computations , Volume 36 (6): 15 – Aug 15, 2019
Download PDF
15 pages

Loading next page...
 
/lp/emerald-publishing/a-study-on-performance-of-mhda-in-training-mlps-40E4v0PsAg
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
0264-4401
DOI
10.1108/ec-05-2018-0216
Publisher site
See Article on Publisher Site

Abstract

In recent years, the application of metaheuristics in training neural network models has gained significance due to the drawbacks of deterministic algorithms. This paper aims to propose the use of a recently developed “memory based hybrid dragonfly algorithm” (MHDA) for training multi-layer perceptron (MLP) model by finding the optimal set of weight and biases.Design/methodology/approachThe efficiency of MHDA in training MLPs is evaluated by applying it to classification and approximation benchmark data sets. Performance comparison between MHDA and other training algorithms is carried out and the significance of results is proved by statistical methods. The computational complexity of MHDA trained MLP is estimated.FindingsSimulation result shows that MHDA can effectively find the near optimum set of weight and biases at a higher convergence rate when compared to other training algorithms.Originality/valueThis paper presents MHDA as an alternative optimization algorithm for training MLP. MHDA can effectively optimize set of weight and biases and can be a potential trainer for MLPs.

Journal

Engineering Computations – Emerald Publishing

Published: Aug 15, 2019

Keywords: Classification; Approximation; Computational complexity; MHDA; MLPs

References

  • Artificial neural network training using a new efficient optimization algorithm
    Askarzadeh, A.; Rezazadeh, A.
  • Advances in design and application of spiking neural networks
    Belatreche, A.; Maguire, L.P.; McGinnity, M.
  • A comparison between gas and PSO in training ANN to model the TE chemical process reactor
    Braik, M.; Sheta, A.; Arieqat, A.
  • Statistical comparisons of classifters over multiple data sets
    Demsar, J.
  • UCI machine learning repository
    Dheeru, D.; Karra Taniskidou, E.
  • Approximation of dynamical systems by continuous time recurrent neural networks
    Funahashi, K.; Nakamura, Y.
  • Artificial neural networks the multilayer perceptron a review of applications in the atmospheric sciences
    Gardner, M.; Dorling, S.
  • On the problem of local minima in back- propagation
    Gori, M.; Tesi, A.
  • Extreme learning machines: a survey
    Huang, G.-B.; Wang, D.H.; Lan, Y.
  • Extreme learning machine: theory and applications
    Huang, G.-B.; Zhu, Q.-Y.; Siew, C.-K.
  • Training neural network with genetic algorithms for forecasting the stock price index
    Kai, F.; Wenhua, X.
  • Particle swarm optimization
    Kennedy, J.
  • Stream flow predictions using nature-inspired firefly algorithms and a multiple model strategy – directions of innovation towards next generation practices
    Khatibi, R.; Pourhosseini, F.A.
  • The self-organizing map
    Kohonen, T.
  • A logical calculus of the ideas immanent in nervous activity
    McCulloch, W.S.; Pitts, W.
  • Artificial neural network model for prediction solar radiation data: application for sizing stand-alone photovoltaic power system
    Mellit, A.; Menghanem, M.; Bendekhis, M.
  • How effective is the grey wolf optimizer in training multi-layer perceptrons
    Mirjalili, S.
  • Dragonfly algorithm: a new meta-heuristic optimization technique for solving single-objective, discrete, and multi-objective problems
    Mirjalili, S.
  • Grey wolf optimizer
    Mirjalili, S.; Mirjalili, S.M.; Lewis, A.
  • Let a biogeography-based optimizer train your multi-layer perceptron
    Mirjalili, S.; Mirjalili, S.M.; Lewis, A.
  • Training feedforward neural networks using genetic algorithms
    Montana, D.J.; Davis, L.
  • Fast convergence for back propagation network with magnified gradient function
    Ng, S.C.; Cheung, C.C.; Leung, S.H.; Luk, A.
  • Universal approximation using radial-basis-function networks
    Park, J.; Sandberg, I.W.
  • Memory based hybrid dragonfly algorithm for numerical optimization problems
    Ranjini, K.S.; Murugan, S.
  • Dimensional analysis and surrogate models for the thermal modeling of multiphysics systems
    Sanchez, F.; Budinger, M.; Hazyuk, I.
  • Optimal unsupervised learning in a single-layer linear feed forward neural network
    Sanger, T.D.
  • An evolutionary extreme learning machine based on group search optimization
    Silva, D.N.G.; Paciftco, L.D.S.; Ludermir, T.B.
  • An ant colony optimization algorithm for continuous optimization: application to feed-forward neural network training
    Socha, K.; Blum, C.
  • Particle swarm optimization: hybridization perspectives and experimental illustrations
    Thangaraj, R.; Pant, M.; Abraham, A.; Bouvry, P.
  • An evolutionary extreme learning machine based on chemical reaction optimization
    Tran, T.V.; Wang, Y.N.
  • Differential evolution for neural networks learning enhancement
    Wdaa, A.S.I.; Sttar, A.
  • No free lunch theorems for optimization
    Wolpert, D.H.; Macready, W.G.
  • Investigation of neural networks for function approximation
    Yang, S.; Ting, T.; Man, K.; Guan, S.-U.