HOPE

Reported on 1 benchmark 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 Vision1 result

Image ClassificationonMNIST
Percentage error· 2015-02-03
0.4
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
Hybrid Orthogonal Projection and Estimation (HOPE): A New Framework to Probe and Learn Neural Networks arXiv:1502.00702