Re:Gaussian Distributions Are Soap Bubbles
by snippyhollow on Saturday November 11, 2017 @12:31PM
(#15677180)
Compulsory "Spikey Spheres" notebook http://nbviewer.jupyter.org/urls/gist.githubusercontent.com/...
[ Parent
| on HN ]
Re:Gaussian Distributions Are Soap Bubbles
by cs702 on Saturday November 11, 2017 @01:00PM
(#15677301)
Yes. t-SNE is probably the only algorithm that might produce "sensible" 2D mappings.
BTW, matplotlib has a nicer facility than add_subplot() for making grid plots:
fig, axes = plot.subplots(nrows=figdims, ncols=figdims)
for dim, ax1 in zip(range(2, MAX_DIM), axes.flatten()[:(MAXDIM-2)]):
.
.
.