VGG8B + LocalLearning + CO

Reported on 3 benchmarks across 1 task · 1 paper

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

Computer Vision3 results

Image ClassificationonMNIST
Percentage error· 2019-01-20
0.26
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
Training Neural Networks with Local Error Signals arXiv:1901.06656
Image ClassificationonSTL-10
Percentage correct· 2019-01-20
80.75
best: 99.64 (µ2Net+ (ViT-L/16))
Training Neural Networks with Local Error Signals arXiv:1901.06656
Image ClassificationonSVHN
Percentage error· 2019-01-20
1.65
best: 1 (E2E-M3)
Training Neural Networks with Local Error Signals arXiv:1901.06656