UnICORNN

Reported on 4 benchmarks across 3 tasks · 1 paper · 3 SOTA

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

Computer Vision2 results

Image Classificationonnoise padded CIFAR-10
% Test Accuracy· 2021-03-09
62.4
SOTA
UnICORNN: A recurrent model for learning very long time dependencies arXiv:2103.05487
Image ClassificationonSequential MNIST
Permuted Accuracy· 2021-03-09
98.4
best: 99.1 (SMPConv)
SOTA
UnICORNN: A recurrent model for learning very long time dependencies arXiv:2103.05487

Time Series1 result

Time Series ClassificationonEigenWorms
% Test Accuracy· 2021-03-09
90.3
best: 92.3 (LEM)
SOTA
UnICORNN: A recurrent model for learning very long time dependencies arXiv:2103.05487

Natural Language Processing1 result

Sentiment AnalysisonIMDb
Accuracy· 2021-03-09
88.4
best: 96.68 (RoBERTa-large with LlamBERT)
UnICORNN: A recurrent model for learning very long time dependencies arXiv:2103.05487