Sciweavers

151 search results - page 1 / 31
» Optimized Approximation Algorithm in Neural Networks Without...
Sort
View
TNN
2008
181views more  TNN 2008»
13 years 4 months ago
Optimized Approximation Algorithm in Neural Networks Without Overfitting
In this paper, an optimized approximation algorithm (OAA) is proposed to address the overfitting problem in function approximation using neural networks (NNs). The optimized approx...
Yinyin Liu, Janusz A. Starzyk, Zhen Zhu
AIA
2007
13 years 6 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
IJCNN
2006
IEEE
13 years 11 months ago
An Evaluation of Over-Fit Control Strategies for Multi-Objective Evolutionary Optimization
— The optimization of classification systems is often confronted by the solution over-fit problem. Solution over-fit occurs when the optimized classifier memorizes the traini...
Paulo Vinicius Wolski Radtke, Tony Wong, Robert Sa...
ICANN
2010
Springer
13 years 5 months ago
Computational Properties of Probabilistic Neural Networks
We discuss the problem of overfitting of probabilistic neural networks in the framework of statistical pattern recognition. The probabilistic approach to neural networks provides a...
Jiri Grim, Jan Hora
ICMLA
2010
13 years 2 months ago
Ensembles of Neural Networks for Robust Reinforcement Learning
Reinforcement learning algorithms that employ neural networks as function approximators have proven to be powerful tools for solving optimal control problems. However, their traini...
Alexander Hans, Steffen Udluft