Počet záznamů: 1
On Combining Robustness and Regularization in Training Multilayer Perceptrons over Small Data
- 1.
SYSNO ASEP 0562371 Druh ASEP C - Konferenční příspěvek (mezinárodní konf.) Zařazení RIV D - Článek ve sborníku Název On Combining Robustness and Regularization in Training Multilayer Perceptrons over Small Data Tvůrce(i) Kalina, Jan (UIVT-O) RID, SAI, ORCID
Tumpach, Jiří (UIVT-O) ORCID, SAI
Holeňa, Martin (UIVT-O) SAI, RIDCelkový počet autorů 3 Zdroj.dok. 2022 International Joint Conference on Neural Networks (IJCNN) Proceedings. - Piscataway : IEEE, 2022 - ISBN 978-1-7281-8671-9 Poč.str. 8 s. Forma vydání Online - E Akce IJCNN 2022: International Joint Conference on Neural Networks /35./ Datum konání 18.07.2022 - 23.07.2022 Místo konání Padua Země IT - Itálie Typ akce WRD Jazyk dok. eng - angličtina Země vyd. US - Spojené státy americké Klíč. slova feedforward networks ; nonlinear regression ; outliers ; robust neural networks ; trend estimation Obor OECD Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8) CEP GA22-02067S GA ČR - Grantová agentura ČR Institucionální podpora UIVT-O - RVO:67985807 UT WOS 000867070905022 EID SCOPUS 85140750378 DOI 10.1109/IJCNN55064.2022.9892510 Anotace Multilayer perceptrons (MLPs) continue to be commonly used for nonlinear regression modeling in numerous applications. Available robust approaches to training MLPs, which allow to yield reliable results also for data contaminated by outliers, have not much penetrated to real applications so far. Besides, there remains a lack of systematic comparisons of the performance of robust MLPs, if their training uses one of regularization techniques, which are available for standard MLPs to prevent overfitting. This paper is interested in comparing the performance of MLPs trained with various combinations of robust loss functions and regularization types on small datasets. The experiments start with MLPs trained on individual datasets, which allow graphical visualizations, and proceed to a study on a set of 163251 MLPs trained on well known benchmarks using various combinations of robustness and regularization types. Huber loss combined with L2 - regularization turns out to outperform other choices. This combination is recommendable whenever the data do not contain a large proportion of outliers. Pracoviště Ústav informatiky Kontakt Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Rok sběru 2023 Elektronická adresa https://dx.doi.org/10.1109/IJCNN55064.2022.9892838
Počet záznamů: 1