Oleg Zabluda's blog
Friday, October 14, 2016
 
Using t-Distributed Stochastic Neighbor Embedding (t-SNE) to visualize high dimensional data is a powerful way to...
Using t-Distributed Stochastic Neighbor Embedding (t-SNE) to visualize high dimensional data is a powerful way to communicate complex information in a more intuitive way. However, while the t-SNE technique is very useful, the visualizations images can be tempting to misread.

In the article below, Martin Wattenberg and Fernanda Viegas of the Google Brain team (g.co/brain) and UX Engineer Ian Johnson walk through a series of simple examples to illustrate what t-SNE diagrams can and cannot show.
http://distill.pub/2016/misread-tsne

Labels:


| |

Home

Powered by Blogger