Evolutionary Algorithms For Neural Networks Binary And Real Data Classification
Journal: International Journal of Scientific & Technology Research (Vol.5, No. 7)Publication Date: 2016-07-15
Authors : Hanan A.R. Akkar; Firas R. Mahdi;
Page : 55-60
Keywords : Artificial neural networks; Classifications; Evolutionary algorithms; Population-based algorithms; Meta-heuristics techniques; and Optimization.;
Abstract
Artificial neural networks are complex networks emulating the way human rational neurons process data. They have been widely used generally in prediction clustering classification and association. The training algorithms that used to determine the network weights are almost the most important factor that influence the neural networks performance. Recently many meta-heuristic and Evolutionary algorithms are employed to optimize neural networks weights to achieve better neural performance. This paper aims to use recently proposed algorithms for optimizing neural networks weights comparing these algorithms performance with other classical meta-heuristic algorithms used for the same purpose. However to evaluate the performance of such algorithms for training neural networks we examine such algorithms to classify four opposite binary XOR clusters and classification of continuous real data sets such as Iris and Ecoli.
Other Latest Articles
- Evolutionary Algorithms Performance Comparison For Optimizing Unimodal And Multimodal Test Functions
- Proximate Composition Energy Content And Sensory Properties Of Complementary Foods Produced From Blends Of Sorghum And African Yam Bean Flour
- Texting As A Discursive Approach For The Production Of Agricultural Solutions
- Design Of A Throw-In Axial Flow Rice Thresher Fitted With Peg And Screw Threshing Mechanism
- Heterogenous Networks HetNets Using Small Cells
Last modified: 2017-06-11 22:50:52