Large RHN

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 ModellingonText8
Bit per Character (BPC)· 2016-07-12
1.27
best: 1.63 (td-LSTM (Zhang et al., 2016))
Recurrent Highway Networks arXiv:1607.03474
Language ModellingonHutter Prize
Bit per Character (BPC)· 2016-07-12
1.27
best: 1.31 (RHN - depth 5 [zilly2016recurrent])
Recurrent Highway Networks arXiv:1607.03474