It is well known that the structure of neural network and the amount of available training data influence the accuracy of developed models; however, the exact character of this relation depends on the chosen problem. Thus, it was decided to analyze what impact these parameters have on the solution of the problem on which we work – the prediction of final height of children treated with growth hormone. It was observed that multilayer perceptron with a wide range of numbers of hidden neurons (from 1 to 100) could solve the problem almost equally well. Thus, this task seems to be rather simple, not requiring complex models. Larger networks tended to produce less accurate results and did not generalize well while working with the data not used in training. Repeating the experiment with the training data set reduced to 50% of its original content, as expected, caused a decrease in accuracy.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
W artykule przedstawiono automatyczne algorytmy optymalizacji architektury sieci neuronowych. W pierwszej części sformułowano problem doboru architektury optymalnej sieci. Następnie przedstawiono teoretyczne aspekty rozważanego problemu. Dalej zaprezentowano wyniki empirycznego doboru architektury sieci w wybranych programach
EN
In this paper the automatic algorithm for optimizing the architecture of artificial neural network is presented. The first part includes the formulation of the selection of optimal architecture of neural network optimization. In the next part the theoretical aspects of the discussed problem. In the concluding point of this article the results of the empirical selection of network architecture in set the selected programs are discussed.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.