Workshop

Slow processes of neurons enable a biologically plausible approximation to policy gradient
Recurrent neural networks underlie the astounding information processing capabilities of the brain, and play a key role in many …
Anand Subramoney, Franz Scherr, Guillaume Bellec, Elias Hajek, Darjan Salaj, Robert Legenstein, Wolfgang Maass
Workshop Homepage Contributed Talk
Eligibility traces provide a data-inspired alternative to backpropagation through time
Learning in recurrent neural networks (RNNs) is most often implemented by gradient descent using backpropagation through time (BPTT), …
Guillaume Bellec, Franz Scherr, Elias Hajek, Darjan Salaj, Anand Subramoney, Robert Legenstein, Wolfgang Maass
OpenReview Workshop Homepage Contributed Talk