hxtorch.spiking.functional.unterjubel

Autograd function to ‘unterjubel’ (german for ‘inject’) hardware observables and allow correct gradient back-propagation.

Basically taken from: https://gerrit.bioai.eu:9443/gitweb?p=model-hx-strobe.git;a=blob;f=src/py/strobe/unterjubel.py;h=4b13de159bd54b629a0b6278cb9c2f58f62883bf;hb=HEAD;js=1

Classes

Unterjubel(*args, **kwargs)

Unterjubel hardware observables to allow correct gradient flow