Sciweavers

323 search results - page 15 / 65
» Effective Training Methods for Function Localization Neural ...
Sort
View
AIA
2007
14 years 11 months ago
Optimizing number of hidden neurons in neural networks
In this paper, a novel and effective criterion based on the estimation of the signal-to-noise-ratio figure (SNRF) is proposed to optimize the number of hidden neurons in neural ne...
Yue Liu, Janusz A. Starzyk, Zhen Zhu
ICONIP
2008
14 years 11 months ago
On Weight-Noise-Injection Training
Abstract. While injecting weight noise during training has been proposed for more than a decade to improve the convergence, generalization and fault tolerance of a neural network, ...
Kevin Ho, Chi-Sing Leung, John Sum
NECO
2002
78views more  NECO 2002»
14 years 9 months ago
Local Overfitting Control via Leverages
We present a novel approach to dealing with overfitting in black-box models. It is based on the leverages of the samples, i.e. on the influence that each observation has on the pa...
Gaétan Monari, Gérard Dreyfus
74
Voted
IJCNN
2000
IEEE
15 years 2 months ago
An Incremental Growing Neural Network and its Application to Robot Control
This paper describes a novel network model, which is able to control its growth on the basis of the approximation requests. Two classes of self-tuning neural models are considered...
A. Carlevarino, R. Martinotti, Giorgio Metta, Giul...
JDCTA
2010
191views more  JDCTA 2010»
14 years 4 months ago
Improved Wavelet Neural Network Based on Hybrid Genetic Algorithm Applicationin on Fault Diagnosis of Railway Rolling Bearing
The method of improved wavelet transform neural network based on hybrid GA(genetic algorithm) is presented to diagnose rolling bearings faults in this paper. Genetic Artificial Ne...
Guoqiang Cai, Limin Jia, Jianwei Yang, Haibo Liu