You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I tried to change the value of dt from 1.0 to 0.1, but it didn't fit in the pipeline with other components. The error I encountered was difference of number of timesteps between encoded input's and network. Since encoded input's number of timesteps is time while network's number of timesteps is time/dt. I was thinking about resolving this issue, but I found that it requires redesigning almost every encoding functions. Any idea about this? Or am I missing something?
Thank you.
The text was updated successfully, but these errors were encountered:
An easy way to fix this is to create a new Pipeline variable self.sim_time = int(time / dt), and pass this into the encoding functions. Or, we could redesign the encoding functions themselves (which are sorely in need of an update anyway) by having them accept a dt argument as well.
After a bit more thought, I think it makes more sense to have all encoding functions accept a dt argument. For example, in the poisson encoding, the spike train generation must depend on the simulation time step in order to achieve the correct firing rates.
I tried to change the value of dt from 1.0 to 0.1, but it didn't fit in the pipeline with other components. The error I encountered was difference of number of timesteps between encoded input's and network. Since encoded input's number of timesteps is
time
while network's number of timesteps istime/dt
. I was thinking about resolving this issue, but I found that it requires redesigning almost every encoding functions. Any idea about this? Or am I missing something?Thank you.
The text was updated successfully, but these errors were encountered: