A novel strategy for speed up training for back propagation algorithm via dynamic adaptive the weight training in artificial neural network

The drawback of the Back Propagation (BP) algorithm is slow training and easily convergence to the local minimum and suffers from saturation training.To overcome those problems, we created a new dynamic function for each training rate and momentum term.In this study, we presented the (BPDRM) algorit...

Ful tanımlama

Detaylı Bibliyografya
Asıl Yazarlar: Al-Duais, Mohameed Sarhan, Yaakub, Abd Razak, Yusoff, Nooraini, Ahmad, Faudziah
Materyal Türü: Makale
Dil:English
Baskı/Yayın Bilgisi: MAXWELL Science Publication 2015
Konular:
Online Erişim:https://repo.uum.edu.my/id/eprint/18613/1/RJASET%209%203%202015%20189-200.pdf