Título:
|
High-Dimensional Brain in a High-Dimensional World: Blessing of Dimensionality
|
Autores:
|
Gorban, Alexander N. ;
Makarov, Valeri A. ;
Tyukin, Ivan Y.
|
Tipo de documento:
|
texto impreso
|
Editorial:
|
MDPI, 2020-01-09
|
Dimensiones:
|
application/pdf
|
Nota general:
|
cc_by
info:eu-repo/semantics/openAccess
|
Idiomas:
|
|
Palabras clave:
|
Estado = Publicado
,
Materia = Ciencias: Informática: Inteligencia artificial
,
Materia = Ciencias: Matemáticas: Cibernética matemática
,
Materia = Ciencias: Matemáticas: Geometría
,
Materia = Ciencias: Matemáticas: Investigación operativa
,
Tipo = Artículo
|
Resumen:
|
High-dimensional data and high-dimensional representations of reality are inherent features of modern Artificial Intelligence systems and applications of machine learning. The well-known phenomenon of the “curse of dimensionality” states: many problems become exponentially difficult in high dimensions. Recently, the other side of the coin, the “blessing of dimensionality”, has attracted much attention. It turns out that generic high-dimensional datasets exhibit fairly simple geometric properties. Thus, there is a fundamental tradeoff between complexity and simplicity in high dimensional spaces. Here we present a brief explanatory review of recent ideas, results and hypotheses about the blessing of dimensionality and related simplifying effects relevant to machine learning and neuroscience.
|
En línea:
|
https://eprints.ucm.es/id/eprint/63012/1/makarov105.pdf
|