Variable projections neural network training

Authors:
V. Pereyra;G. Scherer;F. Wong
Affiliations:
Weidlinger Associates Inc., Mountain View, CA;University of Reading, Mathematics Department;Weidlinger Associates Inc., Mountain View, CA
Venue:
Mathematics and Computers in Simulation - Special issue: Applied and computational mathematics - selected papers of the fifth PanAmerican workshop - June 21-25, 2004, Tegucigalpa, Honduras
Year:
2006

Citing 8
Cited 2

Software for estimating sparse Jacobian matrices

ACM Transactions on Mathematical Software (TOMS)
Ill-conditioning in neural network training problems

SIAM Journal on Scientific Computing
Rank-deficient and discrete ill-posed problems: numerical aspects of linear inversion

Rank-deficient and discrete ill-posed problems: numerical aspects of linear inversion
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Fitting Nature's Basic Functions Part III: Exponentials, Sinusoids, and Nonlinear Least Squares

Computing in Science and Engineering
Large scale least squares scattered data fitting

Applied Numerical Mathematics
Radial Basis Functions

Radial Basis Functions
A generalized learning paradigm exploiting the structure of feedforward neural networks

IEEE Transactions on Neural Networks

Fast computation of equispaced Pareto manifolds and Pareto fronts for multiobjective optimization problems

Mathematics and Computers in Simulation
Aircraft design optimization

Mathematics and Computers in Simulation

Quantified Score

Hi-index	0.00

Visualization

Abstract

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