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...
Saved in:
Main Author: | Rengasamy, Renugah |
---|---|
Format: | Thesis |
Language: | English |
Published: |
2008
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/9460/1/VikneshRamamoorthyMFSKSM2008.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
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) -
A fusion between divergence algorithm and back propagation neural network for segmentation of connected speech
by: Salam, Md. Sah
Published: (2010) -
Enhanced genetic algorithm-based back propagation neural network to diagnose conditions of multiple-bearing system
by: Wulandhari, Lili Ayu
Published: (2014) -
Back propagation neural network and non-linear regression models for dengue outbreak prediction
by: Husin, Nor Azura
Published: (2008) -
Real-time persian handwritten character recognition using back propagation with multilayer perceptron neural network
by: Harouni, Majid
Published: (2009)