Evolving neural networks using bird swarm algorithm for data classification and regression applications
View/ Open
File version
Accepted Manuscript (AM)
Author(s)
Aljarah, Ibrahim
Faris, Hossam
Mirjalili, Seyedali
Al-Madi, Nailah
Sheta, Alaa
Mafarja, Majdi
Griffith University Author(s)
Year published
2019
Metadata
Show full item recordAbstract
This work proposes a new evolutionary multilayer perceptron neural networks using the recently proposed Bird Swarm Algorithm. The problem of finding the optimal connection weights and neuron biases is first formulated as a minimization problem with mean square error as the objective function. The BSA is then used to estimate the global optimum for this problem. A comprehensive comparative study is conducted using 13 classification datasets, three function approximation datasets, and one real-world case study (Tennessee Eastman chemical reactor problem) to benchmark the performance of the proposed evolutionary neural network. ...
View more >This work proposes a new evolutionary multilayer perceptron neural networks using the recently proposed Bird Swarm Algorithm. The problem of finding the optimal connection weights and neuron biases is first formulated as a minimization problem with mean square error as the objective function. The BSA is then used to estimate the global optimum for this problem. A comprehensive comparative study is conducted using 13 classification datasets, three function approximation datasets, and one real-world case study (Tennessee Eastman chemical reactor problem) to benchmark the performance of the proposed evolutionary neural network. The results are compared with well-regarded conventional and evolutionary trainers and show that the proposed method provides very competitive results. The paper also considers a deep analysis of the results, revealing the flexibility, robustness, and reliability of the proposed trainer when applied to different datasets.
View less >
View more >This work proposes a new evolutionary multilayer perceptron neural networks using the recently proposed Bird Swarm Algorithm. The problem of finding the optimal connection weights and neuron biases is first formulated as a minimization problem with mean square error as the objective function. The BSA is then used to estimate the global optimum for this problem. A comprehensive comparative study is conducted using 13 classification datasets, three function approximation datasets, and one real-world case study (Tennessee Eastman chemical reactor problem) to benchmark the performance of the proposed evolutionary neural network. The results are compared with well-regarded conventional and evolutionary trainers and show that the proposed method provides very competitive results. The paper also considers a deep analysis of the results, revealing the flexibility, robustness, and reliability of the proposed trainer when applied to different datasets.
View less >
Journal Title
Cluster Computing
Copyright Statement
© 2019 Springer Berlin / Heidelberg. This is an electronic version of an article published in Cluster Computing, AOV. Cluster Computing is available online at: http://link.springer.com// with the open URL of your article.
Note
This publication has been entered into Griffith Research Online as an Advanced Online Version.
Subject
Distributed computing and systems software