Gal & Ghahramani (2016) - Variational LSTM (medium)

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

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

Medical2 results

Language ModellingonPenn Treebank (Word Level)
Validation perplexity· 2015-12-16
81.9
best: 36.1 (BERT-Large-CAS)
SOTA
A Theoretically Grounded Application of Dropout in Recurrent Neural Networks arXiv:1512.05287
Language ModellingonPenn Treebank (Word Level)
Test perplexity· 2015-12-16
79.7
best: 20.5 (GPT-3 (Zero-Shot))
A Theoretically Grounded Application of Dropout in Recurrent Neural Networks arXiv:1512.05287