Sciweavers

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

12

MCS
2006
Springer

favoriteEmaildiscussreport

86views Pattern Recognition» more MCS 2006»

Variable projections neural network training

13 years 4 months ago

Variable projections neural network training

Download www.csrc.sdsu.edu

8 The training of some types of neural networks leads to separable non-linear least squares problems. These problems may be9 ill-conditioned and require special techniques. A robust algorithm based on the Variable Projections method of Golub and Pereyra10 is designed for a class of feed-forward neural networks and tested on benchmark examples and real data.11

V. Pereyra, G. Scherer, F. Wong

Real-time Traffic

Feed-forward Neural Networks | MCS 2006 | Neural Networks | Pattern Recognition | Variable Projections Method |

claim paper

Related Content

» Clustering neural spike trains with transient responses

» Longterm prediction of time series using NNEbased projection and OPELM

» Almost Random Projection Machine

» Training of LargeScale FeedForward Neural Networks

» A Variable NodetoNodeLink Neural Network and Its Application to HandWritten Recognition

» Neural Network Ensembles from Training Set Expansions

» A Wrapper for Projection Pursuit Learning

» NeuroIG A Hybrid System for Selection and Elimination of Predictor Variables and non Relev...

» Visualizing and Analyzing Multidimensional Output from MLP Networks via Barycentric Projec...

Post Info
More Details (n/a)

Added	14 Dec 2010
Updated	14 Dec 2010
Type	Journal
Year	2006
Where	MCS
Authors	V. Pereyra, G. Scherer, F. Wong

Comments (0)