RMDL (30 RDLs)

Reported on 4 benchmarks across 2 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 Vision3 results

Image ClassificationonMNIST
Accuracy· 2018-05-03
99.82
best: 99.87 (Branching/Merging CNN + Homogeneous Vector Capsules)
SOTA
RMDL: Random Multimodel Deep Learning for Classification arXiv:1805.01890
Image ClassificationonMNIST
Percentage error· 2018-05-03
0.18
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
SOTA
RMDL: Random Multimodel Deep Learning for Classification arXiv:1805.01890
Image ClassificationonCIFAR-10
Percentage correct· 2018-05-03
91.21
best: 99.5 (ViT-H/14)
RMDL: Random Multimodel Deep Learning for Classification arXiv:1805.01890

Methodology1 result

Unsupervised Pre-trainingonUCI measles
Sensitivity (VEB)· 2018-05-03
90.69
SOTA
RMDL: Random Multimodel Deep Learning for Classification arXiv:1805.01890