[p1esk]

What do you mean by “size”? Gzipped size? If you simply look at how dark a Mnist image is (count the percentage of dark pixels) you’ll get about 20% accuracy, which is twice better than random guess but a long way from 90’ish %.

[yvdriess]

What do you mean with accuracy here? Usually 50% accuracy means cointoss, meaning 20% accuracy is equal to 80% accuracy, which is better than the article's 78% and not that far from 90%.

[Frotag]

> meaning 20% accuracy is equal to 80% accuracy,

Only if your model is outputting a yes/no answer right? And that your definition of accuracy is "class with highest probability" (and not "N classes with highest prob")

If your dataset has more than 2 classes like MNIST, a super low accuracy only tells you to ignore the class the model guesses. It doesn't tell you which of the remaining classes is correct

[rjh29]

There are ten choices, so getting the answer right 20% of the time is very plausible.

[tysam_and]

"One simple trick to beat the statistical odds...."

[p1esk]

There are 10 classes in Mnist. Random guess would is 10%.