activity
20182022
most citedNon-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics

19 citations · 66 across the 7 of their papers we have counts for

collaborators
Showing 2018Show all

1 paper · 1 filter

stat.ML2018★ 12 cited

h-detach: Modifying the LSTM Gradient Towards Better Optimization

Devansh Arpit, Bhargav Kanuparthi, Giancarlo Kerg +3

Recurrent neural networks are known for their notorious exploding and vanishing gradient problem (EVGP). This problem becomes more evident in tasks where the information needed to…