Superkernels for RBF Networks Initialization (Short Paper)

0494463 - ÚI 2019 RIV CH eng C - Konferenční příspěvek (zahraniční konf.)
Coufal, David
Superkernels for RBF Networks Initialization (Short Paper).
Artificial Neural Networks and Machine Learning – ICANN 2018. Proceedings, Part II. Cham: Springer, 2018 - (Kůrková, V.; Manolopoulos, Y.; Hammer, B.; Iliadis, L.; Maglogiannis, I.), s. 621-623. Lecture Notes in Computer Science, 11140. ISBN 978-3-030-01420-9.
[ICANN 2018. International Conference on Artificial Neural Networks /27./. Rhodes (GR), 04.10.2018-07.10.2018]
Grant CEP: GA ČR(CZ) GA18-23827S
Institucionální podpora: RVO:67985807
Klíčová slova: Regression task * Nonparametric estimation * Superkernel
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
https://link.springer.com/content/pdf/bbm%3A978-3-030-01421-6%2F1.pdf

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].
Trvalý link: http://hdl.handle.net/11104/0287651