GANN system to optimize both topology and neural weights of a feedforward neural network
| Autor: | Florin Popescu, Iulian-Constantin Vizitiu |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
Physical neural network
Quantitative Biology::Neurons and Cognition Artificial neural network business.industry Time delay neural network Computer science Computer Science::Neural and Evolutionary Computation Machine learning computer.software_genre Topology Statistical classification Probabilistic neural network ComputingMethodologies_PATTERNRECOGNITION Recurrent neural network Feedforward neural network ComputingMethodologies_GENERAL Artificial intelligence business Stochastic neural network computer Nervous system network models |
| Zdroj: | 2010 8th International Conference on Communications. |
| DOI: | 10.1109/iccomm.2010.5509105 |
| Popis: | An interesting approach to improve the quality of the artificial neural network architectures included into a large spectrum of applications, is to use the GANN (Genetic Algorithm Neural Network) system concept. Consequently, a specific genetic technique which simultaneously optimizes both topology and neural weights of a feedforward neural network is described. Finally, to confirm the broached theoretical aspects, a real training database was also used. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|