Multilayer perceptron applied to genotypes classification in diallel studies

In the last decades, a new trend to use more refined analytical procedures, such as artificial neural networks (ANN), has emerged be most accurate, efficient, and extensively applied for mining data prediction in different contexts, including plant breeding. Thus, this study was developed establish classification proposal targeting genotypes breeding programs approach classical models, complete diallel modern techniques. The based on standard deviation values of an interpopulation it also verified possibility training network with standardized genetic parameters discrete scale. We used 12 intercrossed maize populations scheme (66 hybrids), evaluated during 2005/2006 crop season three environments southern Brazil. implemented MLP architecture other associated allowed development generalist model genotype classification. efficient predicting parental hybrid classifications from average components diallel, regardless evaluation environment.