Training of feedforward neural networks for data classification using hybrid particle swarm optimization, Mantegna Lévy flight and neighborhood search

Omid Tarkhaneh; Haifeng Shen

doi:10.1016/j.heliyon.2019.e01275

Back

Training of feedforward neural networks for data classification using hybrid particle swarm optimization, Mantegna Lévy flight and neighborhood search

Journal article

Open access

Peer reviewed

Training of feedforward neural networks for data classification using hybrid particle swarm optimization, Mantegna Lévy flight and neighborhood search

Omid Tarkhaneh and Haifeng Shen

Heliyon, Vol.5(4), e01275

04/2019

DOI: https://doi.org/10.1016/j.heliyon.2019.e01275

PMCID: PMC6449775

PMID: 30993220

Files and links (2)

pdf

Training of feedforward neural networks for data classification using hybrid particle swarm optimization, Mantegna Lévy flight and neighborhood search1.42 MBDownload View

Published (Version of record)CC BY-NC-ND V4.0, Open Access

url

Training of feedforward neural networks for data classification using hybrid particle swarm optimization, Mantegna Lévy flight and neighborhood searchView

Published (Version of record)CC BY-NC-ND V4.0, Open

Metrics

3 Record Views

35 Times Cited - Web of Science

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

Source: InCites

Abstract

Computer science

Artificial Neural networks (ANNs) are often applied to data classification problems. However, training ANNs remains a challenging task due to the large and high dimensional nature of search space particularly in the process of fine-tuning the best set of control parameters in terms of weight and bias. Evolutionary algorithms are proved to be a reliable optimization method for training the parameters. While a number of conventional training algorithms have been proposed and applied to various applications, most of them share the common disadvantages of local optima stagnation and slow convergence. In this paper, we propose a new evolutionary training algorithm referred to as LPSONS, which combines the velocity operators in Particle Swarm Optimization (PSO) with Mantegna Lévy distribution to produce more diverse solutions by dividing the population and generation between different sections of the algorithm. It further combines Neighborhood Search with Mantegna Lévy distribution to mitigate premature convergence and avoid local minima. The proposed algorithm can find optimal results and at the same time avoid stagnation in local optimum solutions as well as prevent premature convergence in training Feedforward Multi-Layer Perceptron (MLP) ANNs. Experiments with fourteen standard datasets from UCI machine learning repository confirm that the LPSONS algorithm significantly outperforms a gradient-based approach as well as some well-known evolutionary algorithms that are also based on enhancing PSO.

Details

Title: Training of feedforward neural networks for data classification using hybrid particle swarm optimization, Mantegna Lévy flight and neighborhood search
Creators: Omid Tarkhaneh - University of Tabriz
Haifeng Shen - Australian Catholic University
Publication Details: Heliyon, Vol.5(4), e01275
Publisher: Elsevier Ltd
Identifiers: 991013176799702368
Academic Unit: Faculty of Science and Engineering
Language: English
Resource Type: Journal article

Training of feedforward neural networks for data classification using hybrid particle swarm optimization, Mantegna Lévy flight and neighborhood search

Files and links (2)

Metrics

UN Sustainable Development Goals (SDGs)

Abstract

Details

Southern Cross University Social media