Limitations of shallow networks representing finite mappings

Limitations of capabilities of shallow networks to efficiently compute real-valued functions on finite domains are investigated. Efficiency is studied in terms of network sparsity and its approximate measures. It is shown that when a dictionary of computational units is not sufficiently large, compu...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural computing & applications 2019-06, Vol.31 (6), p.1783-1792
1. Verfasser:	Kůrková, Věra
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial Intelligence Computational Biology/Bioinformatics Computational Science and Engineering Computer Science Conditioning Data Mining and Knowledge Discovery Domains Image Processing and Computer Vision Mathematical functions Networks Polynomials Probability and Statistics in Computer Science S.i. : Eann 2017
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!