Abstract An innovative method of testing the artificial neural network's effectiveness for ITK inhibitor data prediction was used. As a comparison, a multiple linear regression model was also developed. Using back propagation training, a multilayer perceptron MLP neural network was given the bioactivity estimate task. It was determined that there were enough buried neurons and that the learning rate was enough based on changes in RMSE. Thus, the final neural network consists of one output variable as the output layer, six input variables, eight hidden neurons, three nodes for bias accounting, and a 0.55 learning rate. To assess the robustness of the neural network model, test set data were forecasted, and forecast accuracy was measured.
Alan : Mühendislik
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|