The tuning of error signal for back-propagation algorithms
Despite of Back-propagation (BP) algorithm existence for almost four decades, it is still widely used in many fields to solve range of real world problems. However, it suffers from slow convergence and tends to trap in local minima. So, an improved two-term error function is proposed to overcome the...
Main Author: | Rengasamy, Renugah |
---|---|
Format: | Thesis |
Language: | English |
Published: |
2008
|
Subjects: | |
Online Access: | http://eprints.utm.my/9460/1/VikneshRamamoorthyMFSKSM2008.pdf |
Similar Items
-
A new fuzzy back-propagation learning method based on derivation of min-max function tuned with genetic algorithms
by: Mashinchi, Mohammad Hadi
Published: (2007) -
Rice yield prediction - a comparison between enhanced back propagation learning algorithms
by: Saad, Puteh, et al.
Published: (2004) -
A fusion between divergence algorithm and back propagation neural network for segmentation of connected speech
by: Salam, Md. Sah
Published: (2010) -
Efficient 3D temperature propagation for laser glass interaction
by: Alias, Norma, et al.
Published: (2008) -
One-dimensional finite element discretization of crack propagation through parallel computation
by: Islam, Md. Rajibul, et al.
Published: (2010)