Search Results for author:
Found 3 papers, 0 papers with code
Stabilizing RNN Gradients through Pre-training
However, analysing deep recurrent networks, we identify a new additive source of exponential explosion that emerges from counting gradient paths in a rectangular grid in depth and time.
Less is More! A slim architecture for optimal language translation
Our method outperforms existing techniques in terms of test loss while simultaneously halving the number of parameters.
Stabilizing Spiking Neuron Training
We show how it can be used to reduce the need of extensive grid-search of dampening, sharpness and tail-fatness of the SG.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
