Some Implications of Interval Approach to Dimension for Network Complexity

Authors: Věra Kůrková
Publication year: 2019
Publication type: Abstrakt
Periodical: ESCIM 2019. Book of Abstracts
Projects: Capabilities and limitations of shallow and deep networks
Bibliographic citation: KŮRKOVÁ, Věra. Some Implications of Interval Approach to Dimension for Network Complexity. In: KÓCZY, L. T., MEDINA, J., eds. ESCIM 2019. Book of Abstracts. Cádiu: University of Cádiz, 2019, S. 59-60. ISBN 978-84-09-14600-0.
ID: 510711

Abstract

An interval approach to the concept of dimension is presented. Implications of exponentially growing quasiorthogonal dimension for estimates of network complexity are analysed. Bounds on correlations of computational tasks represented by high-dimensional vectors are derived. Network complexity is analyzed from the point of view od the concentration of measure phenomen.