Perceptron with a tensor train layer

Reported on 2 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 Vision2 results

Image ClassificationonMNIST
Accuracy· 2015-09-22
98.2
best: 99.87 (Branching/Merging CNN + Homogeneous Vector Capsules)
SOTA
Tensorizing Neural Networks arXiv:1509.06569
Image ClassificationonMNIST
Percentage error· 2015-09-22
1.8
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
Tensorizing Neural Networks arXiv:1509.06569