most citedSparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networks

3 citations · 5 across the 2 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2023★ 2 cited

Gradient Flossing: Improving Gradient Descent through Dynamic Control of Jacobians

Rainer Engelken

Training recurrent neural networks (RNNs) remains a challenge due to the instability of gradients across long time horizons, which can lead to exploding and vanishing gradients. Re…