THE EFFECT OF THE NUMBER OF HIDDEN LAYERS IN THE BACKPROPAGATION IN CASE STUDY WEATHER CLASSIFICATION

In this modern era, there are many algorithms that can be used to classify the weather, one of is Backpropagation. Using Backpropagation, research were using temperature, pressure, humidity, wind speed, rain and clouds as input parameters. And output clear, rain. Backpropagation consists learning process testing process. The get optimal weight test classification from Data was in 1600 data (80%) for 400 (20%) This with 1, 2 3 hidden layer examine accuracy result weather classification. As a result, no significant changes percentage on layers. But, more number it used, epoch requires.