EGRU

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

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

Computer Vision1 result

Gesture RecognitiononDVS128 Gesture
Accuracy (%)· uses extra data· 2022-06-13
97.8
best: 100 (TENNs-PLEIADES)
SOTA
Efficient recurrent architectures through activity sparsity and sparse back-propagation through time arXiv:2206.06178

Medical1 result

Language ModellingonWikiText-2
Test perplexity· 2022-06-13
68.9
best: 8.21 (SparseGPT (175B, 50% Sparsity))
Efficient recurrent architectures through activity sparsity and sparse back-propagation through time arXiv:2206.06178