Computational Intelligence and Mathematics for Tackling Complex Problems 2

0549873 - ÚI 2023 RIV CH eng M - Část monografie knihy
Kůrková, Věra
Some Implications of Interval Approach to Dimension for Network Complexity.
Computational Intelligence and Mathematics for Tackling Complex Problems 2. Cham: Springer, 2022 - (Cornejo, M.; Kóczy, L.; Medina-Moreno, J.; Moreno-García, J.), s. 113-119. Studies in Computational Intelligence, 955. ISBN 978-3-030-88816-9
Grant CEP: GA ČR(CZ) GA18-23827S
Institucionální podpora: RVO:67985807
Klíčová slova: Quasiorthogonal dimension * Sparsity of feedforward networks * High-dimensional geometry * Concentration of measure * Covering numbers
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

An interval approach to the concept of dimension is presented. Implications of exponentially growing quasiorthogonal dimension for estimates of network complexity are analyzed. Bounds on correlations of computational tasks represented by high-dimensional vectors are derived. Network complexity is explored from the point of view of the concentration of measure phenomenon.
Trvalý link: http://hdl.handle.net/11104/0325766