The Harmony Search Algorithm for Supervised Training of Neural Network : Design & Implementation

Ali Kattan

ISBN 10: 6139472555 / ISBN 13: 9786139472550

Published by LAP LAMBERT Academic Publishing, 2019

About this Item

nach der Bestellung gedruckt Neuware - Printed after ordering - Within the field of Artificial Intelligence, there are basically two paradigms for the supervised training of Feed-forward Artificial Neural Network (FFANN): the trajectory-driven paradigm, such as Backpropagation, and the evolutionary Stochastic Global Optimization paradigm (SGO), such as Genetic Algorithm. One of the relatively young SGO methods is the Harmony Search (HS) algorithm, which draws its inspiration not from biological or physical processes but from the improvisation process of Jazz musicians. HS was reported to be competitive alternative to other SGO methods. It has been used successfully in many applications mostly in engineering and industry. In this work the HS algorithm is adapted for the supervised training of FFANN and the performance is evaluated using different benchmarking problems. Two enhancements are introduced to achieve better convergence condition and better performance. A parallel implementation is also included along with performance analysis.

Seller Inventory # 9786139472550

Bibliographic Details

• Title: The Harmony Search Algorithm for Supervised Training of Neural Network : Design & Implementation
• Publisher: LAP LAMBERT Academic Publishing
• Publication Date: 2019
• Language: English
• ISBN 10: 6139472555
• ISBN 13: 9786139472550
• Binding: Taschenbuch
• Condition: Neu

About this title

Synopsis

Within the field of Artificial Intelligence, there are basically two paradigms for the supervised training of Feed-forward Artificial Neural Network (FFANN): the trajectory-driven paradigm, such as Backpropagation, and the evolutionary Stochastic Global Optimization paradigm (SGO), such as Genetic Algorithm. One of the relatively young SGO methods is the Harmony Search (HS) algorithm, which draws its inspiration not from biological or physical processes but from the improvisation process of Jazz musicians. HS was reported to be competitive alternative to other SGO methods. It has been used successfully in many applications mostly in engineering and industry. In this work the HS algorithm is adapted for the supervised training of FFANN and the performance is evaluated using different benchmarking problems. Two enhancements are introduced to achieve better convergence condition and better performance. A parallel implementation is also included along with performance analysis.