%0 Conference Proceedings
%@holdercode {isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S}
%B International Geoscience and Remote Sensing Symposium, (IGARSS).
%X The use of feedback in Back Propagation Neural networks satellite imagery landcover 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 a l l weights of the last step's final configuration. The final answer would be a subset of weights corresponding to one of the networks.
%T On Initialization of Backpropagation Neural Networks for Land Cover Classification Using Satellite Imageries
%@secondarytype PRE CI
%@nexthigherunit 8JMKD3MGPCW/3EUAPES
%K Neural networks, Backscaterring, Land cover, Satellite imagery, REMOTE SENSING.
%@usergroup administrator
%@usergroup rosemary@crn.inpe.br
%@group CRN-INPE-MCT-BR
%@e-mailaddress rosemary@crn.inpe.br
%@secondarykey INPE--PRE/
%F self-archiving-INPE-MCTI-GOV-BR
%2 sid.inpe.br/mtc-m17@80/2007/08.14.17.58.02
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%P 902-904
%4 sid.inpe.br/mtc-m17@80/2007/08.14.17.58
%@documentstage not transferred
%D 1993
%S Proceedings
%A Barros, Maria Suelena Santiago,
%A Nowosad, Alexandre Guirland,
%A Amorim, Maria Conceicao de Andrade,
%C Tokyo, Japan
%@area MET