Question on the radius. about minisom

[youyinnn]

I think this is how the neighbourhood radius decreases along the iteration.

minisom/minisom.py

Line 339 in e2efa8e

sig = self._decay_function(self._sigma, t, max_iteration)

And the decay function is the asymptotic_decay.

Here's the plot of plt.plot([asymptotic_decay(0.5, i, 1000) for i in range(1000)]).

[JustGlowing]

@mr-d3falt the radius is defined as sigma and it decreases at each training step as described here: https://github.com/JustGlowing/minisom/blob/master/minisom.py#L116