Article citationsMore >>

H.M. Hassan “On Quantifying Learning Creativity Using Artificial Neural Networks (A Mathematical Programming Approach)” published at CCCT 2007 conference held on July 12-17,2007-Orlando,Florida,USA.

has been cited by the following article:

Article

Analytical Comparison of Swarm Intelligence Optimization versus Behavioral Learning Concepts Adopted by Neural Networks (An Overview)

1Currently with Al-Baha University, Faculty of Eng., Computer Eng. Department (K.S.A), On leave from Faculty of Specified Education-Banha University Egypt


American Journal of Educational Research. 2015, Vol. 3 No. 7, 800-806
DOI: 10.12691/education-3-7-2
Copyright © 2015 Science and Education Publishing

Cite this paper:
Hassan M. H. Mustafa. Analytical Comparison of Swarm Intelligence Optimization versus Behavioral Learning Concepts Adopted by Neural Networks (An Overview). American Journal of Educational Research. 2015; 3(7):800-806. doi: 10.12691/education-3-7-2.

Correspondence to: Hassan  M. H. Mustafa, Currently with Al-Baha University, Faculty of Eng., Computer Eng. Department (K.S.A), On leave from Faculty of Specified Education-Banha University Egypt. Email: Prof.dr.hassanmoustafa@gmail.com

Abstract

Generally, in nature, non-human creatures perform adaptive behaviors to external environment they are living in. i.e. animals have to keep alive by improving their intelligent behavioral ability to be adaptable to their living environmental conditions. This paper presents an investigational comparative overview on adaptive behaviors associated with two diverse biological systems (Neural and Non-Neural). In more details, intelligent behavioral performance of Ant Colony System () in order to reach optimal solution of Traveling Sales-man Problem (TSP) is considered. That's investigated herein versus concepts of adaptive behavioral learning concerned with some animals (cats, dogs, and rats), in order to keep survive. More precisely, investigations of behavioral observations tightly related to suggested animals, supposed to obey discipline of biological information processing. So, Artificial Neural Network () modeling is a relevant tool to investigate such biological system observations. Moreover, an illustrative brief of optimal intelligent behaviors to solve is presented. Additionally, considering effect of noisy environment on learning convergence, an interesting analogy between both proposed biological systems is introduced. Finally, performance of three learning algorithms shown to be analogously in agreement with behavioral concepts of both suggested biological systems' performance.

Keywords