weidel-p
weidel-p
I realized that the solution only works for tutorial 02, for the other tutorials things get more complex because Processes get overwritten. There is some cleanup necessary, but @awintel, could...
We are aware that there are issues with running the tutorial under Windows. This is due to a problem in the combination between Windows, Jupyter notebook and the multiprocessing library....
Thanks for this bug report. I was able to reproduce the faulty behavior in the current version 0.4 but the problem seems already to be resolved in the current main...
In the latest changes I addressed some of the comments above: - renamed UC/HC learning rules to 2F resp. 3F. I think this sounds better - renamed the run_spk function...
Regarding the correct place for the high level learning rules such as STDP. Strictly speaking, @gkarray is correct, they are not Processes, so they should be somewhere else. But in...
I took a look and it's difficult to reproduce this behavior for me. The simulation gets slower and slower and after only a couple hundred of iterations it's unbearably slow....
Yes, that got fixed. I close the issue.
May I add that there was development in respect of setting weights during runtime. So now you can initialize your network once and set the weights each iteration instead of...
yes. The only other change you need to do in this script to make it truly equivalent to the one you posted initially is to reset the states (u and...
Thanks for the fast reply. That would be great! :+1: