modulatory weight
A Methods
It is straightforward to compute. The following derivation leads to our learning rule. We expand on our explanation for step (a) approximation. Here, we simply use the i.i.d. To put this derivation in terms of biological components, we make the following further approximations.
Biologically-plausible backpropagation through arbitrary timespans via local neuromodulators Y uhan Helena Liu 1,2,3,*, Stephen Smith
Here, we propose that extra-synaptic diffusion of local neuromodulators such as neuropeptides may afford an effective mode of back-propagation lying within the bounds of biological plausibility.