Abstract
Abstract 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.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call