Monday, November 25, 2013
Visualizing High Dimensional Data (PCA, LLE, t-SNE)
Here is a Great talk about data visualization: Visualizing Data Using t-SNE - YouTube
Here is the PCA 2 dimension reduction of mnist data (digit 28x28).
Now with a better transformation to keep distance function.
LLE (collapse many points to one)
So now, what is better in the context of unlabeled data?
You can now use t-SNE to visualize millions of objects. Very exciting! http://arxiv.org/abs/1301.3342
article:Visualizing Data using t-SNE