期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：1992
卷号：XXIX Part B3
页码：17-24
出版社：Copernicus Publications
摘要：Structure of neuron networks withdifferent types of interconnections is described.Analitical method, based on nonlinear spectralrepresentation of optical information is used toclassify real signals and objects corresponding tothem. The important idea of time evolution ofspectral parameters is then introduced and it isshown that the problem of parallel signal processingcan be solved with the aid of large number ofidentical elements with nonlinear interconnections.Problems, connected with distortion and signalcorrection as well qualitatively discussed.It isinvestigated influence of losses along network onsignal propagation. Main characteristics of nonlinearneuron network were marked out.2 D neuron networkswith nonlinear interconnections for analysis ofdatas were investigated as well.Models of realneuronlike elements were suggested. Their regimeswere investigated, simulating neurons with the aidof digital computer.E:
