Number of the records: 1
Superkernels for RBF Networks Initialization (Short Paper)
- 1.
SYSNO ASEP 0494463 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Superkernels for RBF Networks Initialization (Short Paper) Author(s) Coufal, David (UIVT-O) RID, SAI, ORCID Source Title Artificial Neural Networks and Machine Learning – ICANN 2018. Proceedings, Part II. - Cham : Springer, 2018 / Kůrková V. ; Manolopoulos Y. ; Hammer B. ; Iliadis L. ; Maglogiannis I. - ISBN 978-3-030-01420-9 Pages s. 621-623 Number of pages 3 s. Publication form Online - E Action ICANN 2018. International Conference on Artificial Neural Networks /27./ Event date 04.10.2018 - 07.10.2018 VEvent location Rhodes Country GR - Greece Event type WRD Language eng - English Country CH - Switzerland Keywords Regression task ; Nonparametric estimation ; Superkernel Subject RIV IN - Informatics, Computer Science OECD category Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8) R&D Projects GA18-23827S GA ČR - Czech Science Foundation (CSF) Institutional support UIVT-O - RVO:67985807 UT WOS 000463338400059 EID SCOPUS 85054854858 Annotation One of the basic tasks solved using artificial neural networks is the regression task. In its canonical form, one seeks for adjusting network’s parameters so that its response on input training data fits the desired outputs reasonably well. Training data {xi, yi}n i=1, n ∈ N consists of points from Rd+1 Euclidean space, i.e., xi ∈ Rd, yi ∈ R. The quality of the fit is typically measured in terms of the mean integrated squared error (MISE). Various regularization techniques are considered to prevent from overfitting. Optimal setting of parameters can be specified analytically in the linear model (linear computational units), however, for the nonlinear units, the network’s parameters are set using different variants of stochastic optimization [1]. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2019 Electronic address https://link.springer.com/content/pdf/bbm%3A978-3-030-01421-6%2F1.pdf
Number of the records: 1