Name
Title | ||
|---|---|---|
On the asymptotic distribution of the least-squares estimators in unidentifiable models. |
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. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1162/08997660460734010 | Neural Computation |
Keywords | DocType | Volume |
asymptotic normality,well-known property,learning machine,simpler model,unidentifiable model,asymptotic distribution,redundant parameter,least-squares estimator,stochastic property,multilayered perceptrons,different result | Journal | 16 |
Issue | ISSN | Citations |
1 | 0899-7667 | 6 |
PageRank | References | Authors |
0.61 | 9 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Taichi Hayasaka | 1 | 94 | 6.83 |
| Masashi Kitahara | 2 | 13 | 1.48 |
| Shiro Usui | 3 | 775 | 198.35 |