SOPCNN (Only a single Model)

Reported on 3 benchmarks across 1 task · 1 paper · 1 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
Percentage error· 2020-01-24
0.17
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
SOTA
Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods arXiv:2001.08856
Image ClassificationonMNIST
Accuracy· 2020-01-24
99.83
best: 99.87 (Branching/Merging CNN + Homogeneous Vector Capsules)
Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods arXiv:2001.08856
Image ClassificationonMNIST
Trainable Parameters· 2020-01-24
1400000
best: 1882602 (Neural Architecture Search (NAS)-enabled Convolutional Neural Network (CNN))
Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods arXiv:2001.08856