In the artificial neural network field, no universal algorithm of modeling ensures obtaining the best possible model for a given task. Researchers frequently regard artificial neural networks with suspicion caused by the lack of repeatability of single experiments. We propose a systematic approach that may increase the probability of finding the optimal network architecture. In the experiments, the average effectiveness in groups of networks rather than single networks should be compared. Such an approach facilitates the analysis of the results caused by changes in the network parameters, while the influence of chance effects becomes negligible. As an example of this protocol, we present optimization of a neural network applied for prediction of persistent facial pain in patients operated for chronic rhinosinusitis. In the stepwise approach, the percentage of correct predictions was gradually increased from 54% to 75% for the external validation set.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Modelling was carried out to investigate the internal dendrite grains structure formation from a liquid two-component solution. For the simulation, our own model and computer program based on CAFD (Cellular Automata - Finite Differences) were used. In modelling, the effect of process conditions and material-related parameters on the nature of the dendritic grain growth was examined. It was demonstrated that increase of the secondary dendrite arm space may by a result of interruption of the arms growth as well as of overgrowing of concave regions. A local melting down of the grains of a solid phase due to the segregation of admixtures reducing the alloy point of liquidus is also possible.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.