From 39e530ed4c0660f2a83e1ba1eb5a59beb2bd06fa Mon Sep 17 00:00:00 2001 From: Bilal Nizami Date: Mon, 26 Mar 2018 15:03:58 +0200 Subject: [PATCH] update docs --- docs/source/pca_tut.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/pca_tut.rst b/docs/source/pca_tut.rst index 916a133..98c7065 100644 --- a/docs/source/pca_tut.rst +++ b/docs/source/pca_tut.rst @@ -162,7 +162,7 @@ Run the following command to perform t-SNE using pairwise RMSD of CA atoms as th Output files include 2D plot of the first 3 PCs, which can be visualize using xmgrace as described earlier. -Note: The t-SNE algorithm is non-linear and highly flexible, which makes it difficults to interpret the results. +Note: The t-SNE algorithm is non-linear and highly flexible, which makes it difficult to interpret the results. Different set of parameters gives very different output. Users are required to try different set of values for “perplexity” , "learning rates", and "number of iteration". A useful discussion covering these issues can be found here https://distill.pub/2016/misread-tsne/