Closed FabianSchubert closed 3 months ago
That branch is only for hidden neurons and, in the standard e-prop framework, output neuron time constant is different from the one which dictates the time constant in the learning rule:
Do you definitely have readout
set for your LeakyIntegrate
output? The only other way I can see that error happening is if you have no other neurons with tau in the network.
Yes, I directly connected a spiking input population to the LeakyIntegrate
output, so indeed there were no other neurons with tau. It was just a linear regression toy model that I was trying to set up, so this error probably doesn't have any practical relevance.
Using
LeakyIntegrate
as an output seems to cause an assertion errorassert self._tau_mem is not None
when trying to compile withEPropCompiler
. My guess is that https://github.com/genn-team/ml_genn/blob/1a27df5c561f40a70783a4b43ff76f0b54e22dbd/ml_genn/ml_genn/compilers/eprop_compiler.py#L419-L420should just include
LeakyIntegrate
so thatcompile_state.tau_mem
is set?