111 citations · 468 across the 32 of their papers we have counts for
Showing 2016Show all
2 papers · 1 filter
stat.ML2016★ 38 cited
Interpretable Recurrent Neural Networks Using Sequential Sparse Recovery
Scott Wisdom, Thomas Powers, James Pitton +1
Recurrent neural networks (RNNs) are powerful and effective for processing sequential data. However, RNNs are usually considered "black box" models whose internal structure and lea…
stat.ML2016★ 111 cited
Full-Capacity Unitary Recurrent Neural Networks
Scott Wisdom, Thomas Powers, John R. Hershey +2
Recurrent neural networks are powerful models for processing sequential data, but they are generally plagued by vanishing and exploding gradient problems. Unitary recurrent neural…