Joaquin Sitte wrote:

> It turns out that the weight vectors of each of the nodes in the SOM are set
> to the SAME random vector, when I expected them to be all DIFFERENT. What is
> wrong with this nested iteration?

You have most likely initialized all your Som instances with the same vectors.
Since your example does not show the initialization, I can't show you where exactly.

Cheers,
Hans-Martin