Metode Peramalan Memakai Jaringan Saraf Buatan Dengan Cara Backpropagation  

Oleh:

Pratama, T. Iwan B.

Jenis: Article from Journal - ilmiah nasional
Dalam koleksi: Jurnal Teknologi Industri vol. 3 no. 2 (Apr. 1999), page 109-116.
Topik: Jaringan Saraf Buatan; Backpropagation

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: JJ83.2 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

Forecasting methods using artificial neutral network is relatively new. These methods offer some improvements especially in efficiency of calculation by massively parallel distributed matrices and vectors calculation using computer systems. The network is trained by some historical data to approximate the pattern of the data. Backpropagation is used to train the network since this learning process has better performance than other supervised learning methods. For forecasting application, the network has two layers with transfer functions of log-sigmoid in the first layer and linear in the second layer. The number of neurons can be varied to be more accurate for giving the forecasted value.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali