Figure 4
From: A rapid and reference-free imputation method for low-cost genotyping platforms
An overview of GRUD model comprising two components: Generator and Discriminator. The generator is a deep network potentially being able to generate unobserved genotypes based on the input of observed variants, and the discriminator tries to distinguish the generated genotype with a haplotype reference panel to determine whether this is a real or fake genotype. RNN: Recurrent neural network.
