Large FS-LSTM-4

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Language ModellingonHutter Prize
Bit per Character (BPC)· 2017-05-24
1.245
best: 1.31 (RHN - depth 5 [zilly2016recurrent])
Fast-Slow Recurrent Neural Networks arXiv:1705.08639
Language Modellingonenwik8
Bit per Character (BPC)· 2017-05-24
1.25
best: 1.67 (LSTM (7 layers))
Fast-Slow Recurrent Neural Networks arXiv:1705.08639