Sciweavers

323 search results - page 2 / 65
» Effective Training Methods for Function Localization Neural ...
Sort
View
IJCNN
2000
IEEE
13 years 9 months ago
Sensitivity Analysis for Conic Section Function Neural Networks
Sensitivity analysis is a method for extracting the cause and effect relationship between the inputs and outputs of the network. After training a neural network, one may want to k...
Lale Özyilmaz, Tülay Yildirim
EOR
2000
77views more  EOR 2000»
13 years 5 months ago
Training the random neural network using quasi-Newton methods
Training in the random neural network (RNN) is generally speci
Aristidis Likas, Andreas Stafylopatis
PAKDD
2000
ACM
161views Data Mining» more  PAKDD 2000»
13 years 9 months ago
Adaptive Boosting for Spatial Functions with Unstable Driving Attributes
Combining multiple global models (e.g. back-propagation based neural networks) is an effective technique for improving classification accuracy by reducing a variance through manipu...
Aleksandar Lazarevic, Tim Fiez, Zoran Obradovic
ANNPR
2006
Springer
13 years 9 months ago
Simple and Effective Connectionist Nonparametric Estimation of Probability Density Functions
Abstract. Estimation of probability density functions (pdf) is one major topic in pattern recognition. Parametric techniques rely on an arbitrary assumption on the form of the unde...
Edmondo Trentin
DATE
2008
IEEE
134views Hardware» more  DATE 2008»
13 years 12 months ago
Scalable Architecture for on-Chip Neural Network Training using Swarm Intelligence
This paper presents a novel architecture for on-chip neural network training using particle swarm optimization (PSO). PSO is an evolutionary optimization algorithm with a growing ...
Amin Farmahini Farahani, Seid Mehdi Fakhraie, Saee...