Lipschitz Recurrent Neural Networks

Benchmark Model Rank Results
sequential-image-classification-on-noise-padded-cifar-10Lipschitz RNN#4% Test Accuracy: 59.0
sequential-image-classification-on-sequential-cifar-10LipschitzRNN#10Unpermuted Accuracy: 64.2
sequential-image-classification-on-sequential-mnistLipschitzRNN#20Permuted Accuracy: 96.3%Unpermuted Accuracy: 99.4