Complexity estimates based on integral transforms induced by computational units

Autoři: RNDr. Věra Kůrková, DSc.
Rok vydání: 2012
Typ publikace: Článek v odborném periodiku
Periodikum: Neural Networks
Projekty: Učení funkcionálních vztahů z vysoce dimenzionálních dat
Bibliografická citace: KŮRKOVÁ, Věra. Complexity estimates based on integral transforms induced by computational units. Neural Networks. 2012, 33(September), 160-167. ISSN 0893-6080. E-ISSN 1879-2782
Dostupné z: doi:10.1016/j.neunet.2012.05.002
DOI: 10.1016/j.neunet.2012.05.002
ID: 377111

Abstrakt

Integral transforms with kernels corresponding to computational units are exploited to derive estimates of network complexity. The estimates are obtained by combining tools from nonlinear approximation theory and functional analysis together with representations of functions in the form of infinite neural networks. The results are applied to perceptron networks.