An efficient adaptive genetic algorithm technique to improve the neural network performance with aid of adaptive GA operators

Katha Kishor Kumar and Suresh Pabboju

International Journal of Networking and Virtual Organisations, 2019, vol. 20, issue 2, 127-142

Abstract: The neural network (NN) performance improvement is one of the major topics. Thus an adaptive genetic algorithm (AGA) technique is proposed by making adaptive with respect to genetic operators like crossover and mutation. Our adaptive GA technique starts with the generation of initial population as same as the normal GA and performs the fitness calculation for each individual generated chromosome. After that, the genetic operator's crossover and mutation will be performed on the best chromosomes. The AGA technique will be utilised in the NN performance improvement process. The AGA will utilise some parameters obtained from the NN by back propagation algorithm. The utilisation of NN parameters by AGA will improve the NN performance. Hence, the NN performance can be improved more effectively by achieving high performance ratio than the conventional GA with NN. The technique will be implemented in the working platform of MATLAB and the results will be analysed to demonstrate the performance of the proposed AGA.

Keywords: adaptive genetic algorithm; AGA; genetic algorithm; GA; back propagation algorithm; BPA; artificial neural network; ANN; crossover and mutation. (search for similar items in EconPapers)
Date: 2019
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=97630 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijnvor:v:20:y:2019:i:2:p:127-142

Access Statistics for this article

More articles in International Journal of Networking and Virtual Organisations from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().