Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

10

ICONIP
2008

favoriteEmaildiscussreport

129views Information Technology» more ICONIP 2008»

On Node-Fault-Injection Training of an RBF Network

13 years 6 months ago

On Node-Fault-Injection Training of an RBF Network

Download web.nchu.edu.tw

Abstract. While injecting fault during training has long been demonstrated as an effective method to improve fault tolerance of a neural network, not much theoretical work has been done to explain these results. In this paper, two different node-fault-injection-based on-line learning algorithms, including (1) injecting multinode fault during training and (2) weight decay with injecting multinode fault, are studied. Their almost sure convergence will be proved and thus their corresponding objective functions are deduced.

John Sum, Chi-Sing Leung, Kevin Ho

Real-time Traffic

Fault Tolerance | ICONIP 2008 | Information Technology | Multinode Fault | On-line Learning Algorithms |

claim paper

Related Content

» RBF networks training using a dual extended Kalman filter

» Improving the Performance of the RBF Neural Networks Trained with Imbalanced Samples

» Online Training of Hierarchical RBF

» Visualization of Hidden Node Activity in Neural Networks II Application to RBF Networks

» Training of Support Vector Machines with Mahalanobis Kernels

» A class of instantaneously trained neural networks

» Normalized Gaussian Radial Basis Function networks

» Visualization of Hidden Node Activity in Neural Networks I Visualization Methods

» Training set optimization in 3D human face recognition by RBF neural networks

Post Info
More Details (n/a)

Added	29 Oct 2010
Updated	29 Oct 2010
Type	Conference
Year	2008
Where	ICONIP
Authors	John Sum, Chi-Sing Leung, Kevin Ho

Comments (0)