| bibtype |
J -
Journal Article
|
| ARLID |
0642808 |
| utime |
20260115095042.5 |
| mtime |
20251209235959.9 |
| SCOPUS |
105005517502 |
| WOS |
001489380800001 |
| DOI |
10.1080/07474946.2025.2498933 |
| title
(primary) (eng) |
From robust neural networks toward robust nonlinear quantile estimation |
| specification |
| page_count |
26 s. |
| media_type |
P |
|
| serial |
| ARLID |
cav_un_epca*0290597 |
| ISSN |
0747-4946 |
| title
|
Sequential Analysis |
| volume_id |
44 |
| volume |
3 (2025) |
| page_num |
350-326 |
|
| keyword |
neural networks |
| keyword |
quantiles |
| keyword |
regression |
| keyword |
outliers |
| keyword |
sequential example selection |
| keyword |
robust statistics |
| author
(primary) |
| ARLID |
cav_un_auth*0345793 |
| name1 |
Kalina |
| name2 |
Jan |
| institution |
UTIA-B |
| full_dept (cz) |
Stochastická informatika |
| full_dept (eng) |
Department of Stochastic Informatics |
| department (cz) |
SI |
| department (eng) |
SI |
| full_dept |
Department of Stochastic Informatics |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| source |
|
| cas_special |
| project |
| project_id |
GA24-10078S |
| agency |
GA ČR |
| country |
CZ |
| ARLID |
cav_un_auth*0472835 |
|
| abstract
(eng) |
Regression quantiles provide a flexible framework for modeling the conditional distribution of a response variable by estimating different parts of its distribution, thereby offering valuable insights into the relationship between predictors and outcomes. However, existing nonlinear regression quantile methods may be sensitive to the presence of severe outliers in the data. This paper starts with investigating robust versions of neural networks. The study includes a proposal of a sequential outlier detection procedure based on sequential example selection for robust neural networks. Further, robust quantile estimators for nonlinear regression is introduced. The proposed quantiles are inspired by least weighted squares regression. To enhance robustness to outliers, they assign implicit weights to individual samples and are specifically tailored for multilayer perceptrons, radial basis function networks, and regularized networks. Numerical experiments demonstrate that the robust quantiles improve generalization and outlier resistance. Simulations confirm that the proposed method outperforms traditional (non-robust) quantiles. |
| result_subspec |
WOS |
| RIV |
IN |
| FORD0 |
10000 |
| FORD1 |
10200 |
| FORD2 |
10201 |
| reportyear |
2026 |
| inst_support |
RVO:67985556 |
| permalink |
https://hdl.handle.net/11104/0372665 |
| confidential |
S |
| mrcbC91 |
C |
| mrcbT16-e |
STATISTICS&PROBABILITY |
| mrcbT16-f |
0.7 |
| mrcbT16-g |
0 |
| mrcbT16-h |
12.4 |
| mrcbT16-i |
0.00028 |
| mrcbT16-j |
0.28 |
| mrcbT16-k |
372 |
| mrcbT16-q |
26 |
| mrcbT16-s |
0.468 |
| mrcbT16-y |
30.39 |
| mrcbT16-x |
0.78 |
| mrcbT16-3 |
60 |
| mrcbT16-4 |
Q2 |
| mrcbT16-5 |
0.500 |
| mrcbT16-6 |
18 |
| mrcbT16-7 |
Q4 |
| mrcbT16-C |
14.7 |
| mrcbT16-M |
0.37 |
| mrcbT16-N |
Q4 |
| mrcbT16-P |
14.7 |
| arlyear |
2025 |
| mrcbU14 |
105005517502 SCOPUS |
| mrcbU24 |
PUBMED |
| mrcbU34 |
001489380800001 WOS |
| mrcbU63 |
cav_un_epca*0290597 Sequential Analysis 44 3 2025 350 326 0747-4946 1532-4176 |
|