Determination of the Best Output Layer Activation Function in Neural Network for Forecasting Peak Discharge
Author(s):
Abstract:
One of the methods to forecast peak discharge among black box method is artificial eural network. Lack of emphatic regulation to architect network is one of disadvantages in neural networks. There is not a suitable criterion to determine number of layer and number of neuron in hidden layer، type of activation function for hidden and output layers and assay and error method is the only solution. In this research، numbers of suitable neurons in this layer and activation function type in output layer for two sub basin، Gatehdeh and Gelinak، situated in Taleghan basin were investigated by perception neural network with three layers and preservation of type of activation function for hidden layer. 20 percentage data for testing stage، 65 percentage data for training stage and 15 percentage data for validation stage were entered in MATLAB software and sigmoid and linear activation functions with the most application in hydrologicsubjects were selected for output layer. Linear function with less RMSE in both stations recognized suitable and the numbers of adequate neurons in Gatehdeh and Gelinak stations were five and six neurons، respectively.
Language:
Persian
Published:
Iranian Journal of Watershed Management Science and Engineering, Volume:4 Issue: 12, 2011
Page:
61
magiran.com/p892168
دانلود و مطالعه متن این مقاله با یکی از روشهای زیر امکان پذیر است:
اشتراک شخصی
با عضویت و پرداخت آنلاین حق اشتراک یکساله به مبلغ 1,390,000ريال میتوانید 70 عنوان مطلب دانلود کنید!
اشتراک سازمانی
به کتابخانه دانشگاه یا محل کار خود پیشنهاد کنید تا اشتراک سازمانی این پایگاه را برای دسترسی نامحدود همه کاربران به متن مطالب تهیه نمایند!
توجه!
- حق عضویت دریافتی صرف حمایت از نشریات عضو و نگهداری، تکمیل و توسعه مگیران میشود.
- پرداخت حق اشتراک و دانلود مقالات اجازه بازنشر آن در سایر رسانههای چاپی و دیجیتال را به کاربر نمیدهد.
In order to view content subscription is required
Personal subscription
Subscribe magiran.com for 70 € euros via PayPal and download 70 articles during a year.
Organization subscription
Please contact us to subscribe your university or library for unlimited access!