A physical theory is not complete until it permits the stuff from our imagination // Per Lindholm
Machine Learning – Getting .8985 Or MNIST With Only 1000 Train vs 69000 Test Samples Using Denoise
I think this denoising is something important. Ran MNIST using denoise_tv_chambolle with only 1000 train samples and got an accuracy of 0.8985. Almost 90% on a very large test set with only 1000 samples.