METODE PERAMALAN JARINGAN SARAF TIRUAN DENGAN MENGGUNAKAN CARA BACKPROPAGATION

Simple item page
dc.contributor.authorFatayat
dc.date.accessioned2014-05-22T04:54:37Z
dc.date.available2014-05-22T04:54:37Z
dc.date.issued2014-05-22
dc.description.abstractForecasting method using Artificial Neural Networks with Backpropagation method starts from defining the input node, the hidden and output, then data is normalized according to the activation function is used. Then it is followed by determining the value of learning rate, error tolerance and maximum iteration values. The network was trained by some of the historical data to approximate the pattern data. Backpropagation is used to train the network because of the learning process has a better performance for the method of learning, which is supervised and is usually used by the perceptron with a lot of layers to change the weights connected to the neurons that exist in the hidden layer. Each node signal processing with activation function is a rule for determining the sum of input to output processing elements through choice. Activation function expressing the relationship between the level internal of activation and output can be either linear or nonlinear. The purpose of this transformation is to modify the output into the range of values. Activation function to be used is the Binary Sigmoid functionen_US
dc.description.sponsorshipSeminar UR-UKM ke-7 2012en_US
dc.identifier.isbn978-602-18936-0-9
dc.identifier.otherwahyu sari yeni
dc.identifier.urihttp://repository.unri.ac.id/xmlui/handle/123456789/6327
dc.language.isoenen_US
dc.subjectNeural network prediction by Backpropagationen_US
dc.titleMETODE PERAMALAN JARINGAN SARAF TIRUAN DENGAN MENGGUNAKAN CARA BACKPROPAGATIONen_US
dc.typeUR-Proceedingsen_US

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
78 makalah oral.pdf
Size:
333.77 KB
Format:
Adobe Portable Document Format
Description:
artikel
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

4.Seminar UR-UKM KE-7 2012