Re: Seeding the random number generator

[james@let.rug.nl]

It turns out the seeding was working fine in the first place...

Having investigated this to the point where I was actually printing weights
out iteration by iteration I found that my networks were all
converging to the same set of weights from different initialisations!

To put this in context, I'm training a 5x5 SOM, for 400 iterations,
with a gradually decreasing circular neighbourhood and learning
rate. 5 runs from different initialisations end up with the same
weights within 100 iterations. However the weights the networks have
still change from iteration to iteration...

The initial learning rate is 0.9 and it reduces by 1/400th of the
initial value each iteration (actually reaches 0 at end of final
iteration). The neighbourhood radius starts at 5 and decreases
similarly, though never goes below 1.

Anyway, should this *ever* happen?! It seems very strange to me...

James