[nonbel]

They say some weird stuff in this paper:

>"Specifically, we take a candidate architecture and train it both on the true data and on a copy of the data in which the true labels were replaced by random labels. In the second case, there is no longer any relationship between the instances and the class labels. As a result, learning is impossible."

This is like saying learning someones phone number is impossible because there is no relationship between the person and the number.

[jimfleming]

It's more like giving you a bag of random house numbers and instructing you to place the numbers on the correct houses in an area you've never been to before. An instructor teaches you where some of the numbers go, and you can memorize those examples, but when the instructor leaves you to finish the job on your own you have no way of knowing how to assign the remaining numbers.

Memorization is pretty easy. Generalizing from past examples requires that there be a relationship not just between one person and their phone number but between all people and their phone numbers.

[nonbel]

Sure, that's an even better example. I guess, try as I might, I cannot grasp what people are finding interesting about this paper.