Learning local discrete features in explainable-by-design convolutional neural networks

Open paper
Benchmark Model Rank Results
image-classification-on-cifar-10R-ExplaiNet-26#156Percentage correct: 94.15Parameters: 0.89 M
image-classification-on-fashion-mnistR-ExplaiNet-26#9Percentage error: 6.55Accuracy: 93.45Trainable Parameters: 892362
image-classification-on-kuzushiji-mnistR-ExplaiNet-26#5Accuracy: 98.78Error: 1.22Trainable Parameters: 892362
image-classification-on-mnistR-ExplaiNet-22 (single model)#6Percentage error: 0.20Accuracy: 99.80Trainable Parameters: 743882
image-classification-on-oracle-mnistR-ExplaiNet-26#2Accuracy: 96.93Trainable Parameters: 892362

Rank counts only results with a code link.