On the asymptotic distribution of the least-squares estimators in unidentifiable models

Authors:
Taichi Hayasaka;Masashi Kitahara;Shiro Usui
Affiliations:
Department of Information and Computer Engineering, Toyota National College of Technology, Toyota, Aichi 471-8525, Japan;Department of Information and Computer Sciences, Toyohashi University of Technology, Toyohashi, Aichi 441-8580, Japan;Laboratory for Neuroinformatics, RIKEN Brain Science Institute, Wako, Saitama 351-0198, Japan
Venue:
Neural Computation
Year:
2004

Citing 6
Cited 2

A regularity condition of the information matrix of a multilayer perceptron network

Neural Networks
Model selection in neural networks

Neural Networks
Upper bound of the expected training error of neural network regression for a Gaussian noise sequence

Neural Networks
On the problem in model selection of neural network regression in overrealizable scenario

Neural Computation
Algebraic Analysis for Nonidentifiable Learning Machines

Neural Computation
Model complexity control for regression using VC generalization bounds

IEEE Transactions on Neural Networks

Relation between weight size and degree of over-fitting in neural network regression

Neural Networks
Equations of states in singular statistical estimation

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In order to analyze the stochastic property of multilayered perceptrons or other learning machines, we deal with simpler models and derive the asymptotic distribution of the least-squares estimators of their parameters. In the case where a model is unidentified, we show different results from traditional linear models: the well-known property of asymptotic normality never holds for the estimates of redundant parameters.