The Net-Input Error Backpropagation and Neuron Splitting for Neural Network
碩士 === 國立臺灣科技大學 === 電機工程系 === 91 === The standard backpropagation learning algorithm suffers from the problem of premature saturation in general. It causes the error to be trapped at the current value and decreases the learning efficiency of neural networks. Many efforts had been put on t...
Main Authors: | YU YA-TING, 游雅婷 |
---|---|
Other Authors: | Shueng-Feng Su |
Format: | Others |
Language: | zh-TW |
Published: |
2003
|
Online Access: | http://ndltd.ncl.edu.tw/handle/06952593464202116590 |
Similar Items
-
Conjugate descent formulation of backpropagation error in feedforward neural networks
by: NK Sharma, et al.
Published: (2009-06-01) -
Convergence of Batch Split-Complex Backpropagation Algorithm for Complex-Valued Neural Networks
by: Huisheng Zhang, et al.
Published: (2009-01-01) -
Backpropagation Neural Network Model for Stock Trading Points Prediction
by: Yi-Ting Lin, et al.
Published: (2011) -
A comparison of the backpropagation and recursive prediction error algorithms for training neural networks
by: Billings, S. A., et al.
Published: (1991) -
The Hardware Implementation of Backpropagation's Neural Network
by: Yean-Nong Yang, et al.
Published: (1993)