Benchmarking an artificial neural network tuned by a genetic algorithm
Year: 2012
Type: article
Abstract: This thesis starts with a brief introduction to neural networks and the tuning of neural networks using genetic algorithms. An improved genetic algorithm is benchmarked using the technical paper Proben1 as a starting point. The benefits of using a genetic algorithm as well as results of the benchmark tests in comparison to a resilient backpropagation algorithm are discussed. The improved genetic algorithm is not a universal solution to all classification problems. Even though it outperforms the resilient backpropagation algorithm slightly in these benchmark tests more benchmarking on more vast solution domains must be performed. Acknowledgments I would like to thank my supervisor Jerry Eriksson for giving me valuable pointers concerning layout and content. I would also like to thank Peter Levander for introducing me to genetic algorithms being used to train artificial neural networks. I am really grateful that I got to participate in the thesis writing group and would like to thank the other members,
Author: Karl Blomström
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W640020014