Document Type : Research Paper
Author
College of Education for pure sciences- University of Anbar
Abstract
In this paper ,we use new treatment ,Differential Evolution,, Differential Evolution (DE) has been used to
determine optimal value for ANN parameters such as learning rate and momentum rate and also for weight
optimization. In ANN, there are many elements need to be considered, and these include the number of input nodes,
hidden nodes, output nodes, learning rate, momentum rate, bias parameter, minimum error and activation/transfer
functions. Three programs have developed; Differential Evolution Neural Network (DENN), Genetic Algorithm Neural
Network (GANN) and Particle Swarm Optimization with Neural Network (PSONN) to probe the impact of these
methods on ANN learning using various datasets. The results have revealed that DENN has given quite promising
results in terms of convergence rate and smaller errors compared to PSONN and GANN.
Keywords
Main Subjects
- Yao, X. (1999). 'Evolving artificial neural networks', Proceedings of the IEEE. vol. 87, no. 9: 1423 -1447.
- Storn,R. and Price,K.: Differential Evolution – A Simple and Efficient Adaptive Scheme for Global Optimization Over Continuous Spaces,Technical Report-95-012,International Computer Science Institute, Berkeley,CA,USA
- Hussein A. Abbass, Ruhul Sarker, and harles Newton. A pareto differential evolution approach to vector optimization problems. In Proceedings of the IEEE Congress on Evolutionary Computation, CEC2001, Seoul, Korea,IEEE Press, 2001.
- Storn,R. and Price,K.: Differential Evolution – A Simple and Efficient Adaptive Scheme for Global Optimization Over ontinuous Spaces,Technical Report TR-95-012,International Computer Science Institute,Berkeley,CA,USA http://www.icsi. berkeley.edu/ techreports/1995.abstracts/tr-95-012.htm), 1995.
- Storn,R. and Price,K.: Differential evolution – a simple and efficient heuristic for global optimization over continuous spaces, Journal of Global Optimization, 11(4) 1997,341–359.
)
