Four-layer spherical self-organized maps neural networks trained by recirculation to simulate perception and abstraction activity : application to patterns of rainfall global reanalysis

Abstract This work is intended to organize a big set of time series. To do that a self-organized map is implemented in four spherical layers trainded by recirculation. This way tries to simulate aspects of perceotion and abstraction. The methodology and the fundamentals are describe. About the funda...

Descripción completa

Detalles Bibliográficos
Autor principal: Huggenberger, Darío Alberto
Formato: Artículo publishedVersion
Lenguaje:Inglés
Inglés
Publicado: 2019
Materias:
Neural NEtworks, Spherical Self-Organized Maps, Recirculation, Perception, Abstraction, Psycho Genetics, Rainfall REanalysis, Climate Variability
Acceso en línea:http://hdl.handle.net/20.500.12272/3441
Aporte de:
RIA - Repositorio Institucional Abierto (UTN) de Universidad Tecnológica Nacional
id I68-R174-20.500.12272-3441
record_format dspace
institution Universidad Tecnológica Nacional
institution_str I-68
repository_str R-174
collection RIA - Repositorio Institucional Abierto (UTN)
language Inglés
Inglés
topic Neural NEtworks, Spherical Self-Organized Maps, Recirculation, Perception, Abstraction, Psycho Genetics, Rainfall REanalysis, Climate Variability
spellingShingle Neural NEtworks, Spherical Self-Organized Maps, Recirculation, Perception, Abstraction, Psycho Genetics, Rainfall REanalysis, Climate Variability
Huggenberger, Darío Alberto
Four-layer spherical self-organized maps neural networks trained by recirculation to simulate perception and abstraction activity : application to patterns of rainfall global reanalysis
topic_facet Neural NEtworks, Spherical Self-Organized Maps, Recirculation, Perception, Abstraction, Psycho Genetics, Rainfall REanalysis, Climate Variability
description Abstract This work is intended to organize a big set of time series. To do that a self-organized map is implemented in four spherical layers trainded by recirculation. This way tries to simulate aspects of perceotion and abstraction. The methodology and the fundamentals are describe. About the fundamentals, both from the problema point of view and the neural aspects as brain functioning, perception and abstraction concepts, psycho genetics and grouping ideas, and from the architecture of the network, scheme of training, spherical layers of the maps and algorithms involved in the iterative training, Then, it is used to organize a big set of time series of rainfall reanalysis on grid point around the Earth to show how it functions. After removing the average from the series, the annual cycle in shape and amplitude is the main criterion for oganization. It is shown how the successive layers contain more general abstractions, their representativeness around the Globe and in regional scale. It is compared with individual series in some points of grid. A posible change of behaviour is found in global scale around 1973 and with a variant in the methodogy a possible change in the annual cycle the same year.
format Artículo
publishedVersion
Artículo
author Huggenberger, Darío Alberto
author_facet Huggenberger, Darío Alberto
author_sort Huggenberger, Darío Alberto
title Four-layer spherical self-organized maps neural networks trained by recirculation to simulate perception and abstraction activity : application to patterns of rainfall global reanalysis
title_short Four-layer spherical self-organized maps neural networks trained by recirculation to simulate perception and abstraction activity : application to patterns of rainfall global reanalysis
title_full Four-layer spherical self-organized maps neural networks trained by recirculation to simulate perception and abstraction activity : application to patterns of rainfall global reanalysis
title_fullStr Four-layer spherical self-organized maps neural networks trained by recirculation to simulate perception and abstraction activity : application to patterns of rainfall global reanalysis
title_full_unstemmed Four-layer spherical self-organized maps neural networks trained by recirculation to simulate perception and abstraction activity : application to patterns of rainfall global reanalysis
title_sort four-layer spherical self-organized maps neural networks trained by recirculation to simulate perception and abstraction activity : application to patterns of rainfall global reanalysis
publishDate 2019
url http://hdl.handle.net/20.500.12272/3441
work_keys_str_mv AT huggenbergerdarioalberto fourlayersphericalselforganizedmapsneuralnetworkstrainedbyrecirculationtosimulateperceptionandabstractionactivityapplicationtopatternsofrainfallglobalreanalysis
bdutipo_str Repositorios
_version_ 1764820551905312770

Ejemplares similares