Chris Eliasmith
Chris Eliasmith
ah kewl, yeah makes sense you could account for the delay!
one specific example is the gate initializations seem swapped, in the sense that you want to start the initialization with a bias of one and a weight of zero (otherwise...
Yup, same debate. It should be easy to implement, as the code for making this happen is in the code... in fact if you go to the nengo_gui preferences you...
The reason this came up in discussion is because of a difference between how new users will encounter nengo, and how it's grown up in the lab. In the lab,...
Sure, we don't necessarily want the GUI to be used for everything, but it would be nice, as to @studywolf's suggestion, to be using as much the same model as...
This remains a critical issue for me still.
So basically you need to make sure that the delay (theta) doesn't get too small (moving the poles leftward) compared to tau (which moves poles rightward as it gets bigger)....
Unfortunately it is often convenient to change the number of neurons... but yeah, if it's causing lots of problems we should probably just force people to remake the population...
it happens for 10 neurons drasmuss wrote: > Does this happen for small populations (like 10 neurons)? It could > just be that it is trying to draw hundreds of...