Many real-world problems are hard to solve due to difficulty in understanding their indirect causes and effects. The solutions are also not trivial since the parameters that influence the structures and dynamics over time are unknown and often impossible to be analytically solved. A Multi-Threaded GA is designed and a comparative study on its performances is presented with the main aim to understand its ability to escaping from local optima. The performances have been tested on the Trap Functions: a complex toy problem used mainly for understanding the dynamics and search ability of EAs.
Multi-Threaded Genetic Algorithm for Escaping Local Optima
PAVONE, MARIO FRANCESCO
2012-01-01
Abstract
Many real-world problems are hard to solve due to difficulty in understanding their indirect causes and effects. The solutions are also not trivial since the parameters that influence the structures and dynamics over time are unknown and often impossible to be analytically solved. A Multi-Threaded GA is designed and a comparative study on its performances is presented with the main aim to understand its ability to escaping from local optima. The performances have been tested on the Trap Functions: a complex toy problem used mainly for understanding the dynamics and search ability of EAs.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
