[avaku]

Thanks for posting this. This looks like something genuinely new. Going to look into it.

[DoctorOetker]

I didn't read the referenced 2017 paper yet, but mapping the training data to noise (gaussian and/or other) is exactly what the RevNet paper does, with the advantage of deterministic reversibility such that the trained RevNet is also generative (without having to do gradient descent for each generated image)

[dtjohnnyb]

The intro to the paper has a nice comparison to other similar methods (generative and non-generative) and the blog post linked in this article by inFERNCe https://www.inference.vc/unsupervised-learning-by-predicting... has a nice comparison at the end to different unsupervised methods and where this method adds novelty (or doesn't!)

[DoctorOetker]

>has a nice comparison at the end to different unsupervised methods

I don't see the comparisons at the end of the inFERENCe link?

[zygotic12]

I think I'm missing the point?

A visual proof that neural nets can compute any function: http://neuralnetworksanddeeplearning.com/chap4.html

[smittywerben]

> looks like something genuinely new

I fear those words