IndRNN

Reported on 2 benchmarks across 2 tasks · 2 papers

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

Time Series1 result

Time Series ClassificationonEigenWorms
% Test Accuracy· 2021-03-09
49.7
best: 92.3 (LEM)
UnICORNN: A recurrent model for learning very long time dependencies arXiv:2103.05487

Medical1 result

Language ModellingonPenn Treebank (Character Level)
Bit per Character (BPC)· 2018-03-13
1.19
best: 1.38 (Bipartite Flow)
Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN arXiv:1803.04831