BinaryConnect

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 ClassificationonCIFAR-10
Percentage correct· 2015-11-02
91.7
best: 99.5 (ViT-H/14)
BinaryConnect: Training Deep Neural Networks with binary weights during propagations arXiv:1511.00363
Image ClassificationonMNIST
Percentage error· 2015-11-02
1
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
BinaryConnect: Training Deep Neural Networks with binary weights during propagations arXiv:1511.00363
Image ClassificationonSVHN
Percentage error· 2015-11-02
2.2
best: 1 (E2E-M3)
BinaryConnect: Training Deep Neural Networks with binary weights during propagations arXiv:1511.00363