Convolutional Tsetlin Machine

Reported on 4 benchmarks across 2 tasks · 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 ClassificationonKuzushiji-MNIST
Accuracy· 2019-05-23
96.3
best: 99.35 (KMNIST-Tiny)
The Convolutional Tsetlin Machine arXiv:1905.09688
Image ClassificationonMNIST
Accuracy· 2019-05-23
99.4
best: 99.87 (Branching/Merging CNN + Homogeneous Vector Capsules)
The Convolutional Tsetlin Machine arXiv:1905.09688
Image ClassificationonMNIST
Percentage error· 2019-05-23
0.6
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
The Convolutional Tsetlin Machine arXiv:1905.09688