%0 Conference Proceedings
%@nexthigherunit 8JMKD3MGPCW/43SKC35
%@holdercode {isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S}
%@resumeid 8JMKD3MGP5W/3C9JHRQ
%@resumeid 8JMKD3MGP5W/3C9JGGN
%@usergroup administrator
%@usergroup jefferson
%3 On initialization_nowosad.pdf
%@secondarykey INPE-11627-PRE/7008
%A Barros, Maria Suelena Santiago,
%A Nowosad, Alexandre Guirland,
%A Andrade Amorin, Maria Conceição de,
%T On initialization of back propagation neural networks for land cover classification using satellite imageries.
%B Geoscience and Remote Sensing Symposium, 1993. IGARSS.
%8 18-21 Aug 1993
%C Tokyo , Japan
%D 1993
%V 2
%P 902-904
%S Anais
%2 cptec.inpe.br/walmeida/2004/12.02.15.29.51
%4 cptec.inpe.br/walmeida/2004/12.02.15.29
%X The use of feedback in back propagation neural networks satellite imagery land cover classification is investigated. Two networks are used and the described method can be considered as a discrete-time stochastic evolutionary process. The input to the process is an imagery pair plus the set of all weights of the last step's final configuration. The final answer would be a subset of weights corresponding to one of the networks
%@language English
%@copyholder SID/SCD
%@e-mailaddress alex@cptec.inpe.br
%@secondarytype PRE CI
%@format Papel, On-line.
%@area MET
%@group DMD-INPE-MCT-BR