%0 Book Section
%@nexthigherunit 8JMKD3MGPCW/3ESGTTP
%@nexthigherunit 8JMKD3MGPCW/3F2PHGS
%3 santos_hybrid.pdf
%@mirrorrepository urlib.net/www/2017/11.22.19.04.03
%4 sid.inpe.br/mtc-m21c/2019/12.27.10.12
%A Santos, Rafael Duarte Coelho dos,
%A Souza, Felipe Carvalho de,
%A Muralikrishna, Amita,
%A Santos Júnior, Walter Augusto dos,
%@secondarytype PRE LI
%B Astronomical data analysis software and systems XXVIII
%D 2019
%E Teuben, P. J.,
%E Pound, M. W.,
%E Thomas, B. A.,
%E Warner, E. M.,
%@secondarykey INPE--/
%I Astronomical Society of the Pacific
%K neural network, galaxy.
%O 28th Annual Conference on Astronomical Data Analysis Software and Systems (ADASS XXVIII), 11-15 nov. 2018, University of Maryland, MD.
%P 103-106
%S Astronomical Society of the Pacific Conference Series
%T A hybrid neural network approach to estimate galaxy redshifts from multi-band photometric surveys
%V 523
%X Machine learning methods have been used in cosmological studies to estimate variables that would be hard or costly to measure precisely, like, for example, estimating redshifts from photometric data. Previous work showed good results for estimating photometric redshifts using nonlinear regression based on an artificial neural network (MultiLayer Perceptron or MLP). In this work we explore a hybrid neural network approach that uses a Self-Organizing Map (SOM) to separate the original data into different groups, then applying the MLP to each neuron on the SOM to obtain different regression models for each group. Preliminary results indicate that in some cases better results can be achieved, although the computational cost may be increased.
%@area COMP
%@electronicmailaddress rafael.santos@inpe.br
%@electronicmailaddress felipe.carvalho@inpe.br
%@electronicmailaddress amita.muralikrishna@inpe.br
%@documentstage not transferred
%@group LABAC-COCTE-INPE-MCTIC-GOV-BR
%@group CAP-COMP-SESPG-INPE-MCTIC-GOV-BR
%@group CAP-COMP-SESPG-INPE-MCTIC-GOV-BR
%@dissemination BNDEPOSITOLEGAL
%@usergroup simone
%@resumeid 8JMKD3MGP5W/3C9JJ4N
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@versiontype publisher
%@holdercode {isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S}
%2 sid.inpe.br/mtc-m21c/2019/12.27.10.12.30