|
This article is cited in 6 scientific papers (total in 6 papers)
On the complexity and dimension of continuous finite-dimensional maps
B. S. Darkhovskyab a Institute for Systems Analysis of Russian Academy of Sciences
b Russian University of Transport
Abstract:
We introduce the concept of $\varepsilon$-complexity of an individual continuous
finite-dimensional map.
This concept is in good accord with the principle of
A. N. Kolmogorov's idea of measuring complexity of objects. It is shown that
the $\varepsilon$-complexity of an “almost all”
Hölder map can be effectively described. This description can be used as a basis
for a model-free technique for segmentation
and classification of data of arbitrary nature. A new definition of the dimension
of the graph of a map
is also proposed.
Keywords:
$\varepsilon$-complexity, continuous maps, model-free classification and segmentation of data.
Received: 06.11.2018 Revised: 25.12.2019 Accepted: 20.01.2020
Citation:
B. S. Darkhovsky, “On the complexity and dimension of continuous finite-dimensional maps”, Teor. Veroyatnost. i Primenen., 65:3 (2020), 479–497; Theory Probab. Appl., 65:3 (2020), 375–387
Linking options:
https://www.mathnet.ru/eng/tvp5267https://doi.org/10.4213/tvp5267 https://www.mathnet.ru/eng/tvp/v65/i3/p479
|
Statistics & downloads: |
Abstract page: | 239 | Full-text PDF : | 66 | References: | 41 | First page: | 12 |
|