Sparsity of Shallow Networks Representing Finite Mappings

0476509 - ÚI 2018 RIV CH eng C - Konferenční příspěvek (zahraniční konf.)
Kůrková, Věra
Sparsity of Shallow Networks Representing Finite Mappings.
EANN 2017. Cham: Springer, 2017 - (Boracchi, G.; Iliadis, L.; Jayne, C.; Likas, A.), s. 337-348. Communications in Computer and Information Science, 744. ISBN 978-3-319-65171-2. ISSN 1865-0929.
[EANN 2017. International Conference /18./. Athens (GR), 25.08.2017-27.08.2017]
Grant CEP: GA ČR GA15-18108S
Institucionální podpora: RVO:67985807
Klíčová slova: shallow networks * finite mappings * sparsity * model complexity * concentration of measure * signum perceptrons
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Limitations of capabilities of shallow networks to represent sparsely real-valued functions on finite domains is investigated. Influence of sizes of function domains and of sizes dictionaries of computational units on sparsity of networks computing finite mappings is explored. It is shown that when dictionary is not sufficiently large with respect to the size of the finite domain, then almost any uniformly randomly chosen function on the domain either cannot be sparsely represented or its computation is unstable.
Trvalý link: http://hdl.handle.net/11104/0272989