Fig. 3
From: A robust nonlinear low-dimensional manifold for single cell RNA-seq data
Comparison of kernel and error models on 11 neural and blood cell populations [33]: Average adjusted rand score (left) and normalized mutual information (right) of ten k-means cluster labels against true cell type labels versus number of latent dimensions learned (legend) NE - normal error model, RBF - radial basis function kernel only, m12 - sum of RBF and Matérn 1/2 kernels, full - sum of RBF, Matérn 1/2, Matérn 3/2, and Matérn 5/2 kernels