Hacker News Reader

Can't believe that FNet paper flew under my radar all this time—what a cool idea! It's remarkable to me that it works so well considering I haven't heard anyone mention it before! Do you know if any follow-up work was done?

View on HN

This is the paper, which appears to be cited in hundreds of others, some of which appear to be about efficiency gains. https://arxiv.org/abs/2105.03824

"Fnet: Mixing tokens with fourier transforms" (2021) https://arxiv.org/abs/2105.03824

https://scholar.google.com/scholar?cites=1423699627588508486...

Fourier Transform and convolution.

Shouldn't a deconvolvable NN be more explainable? #XAI

Deconvolution: https://en.wikipedia.org/wiki/Deconvolution

I know AI is moving fast but they were only published within the last month or three.

I was referring to link [1] in GP’s comment, which is to a paper published in 2021, not to either of the more recent papers they published.

Oops, apologies.

Reply on news.ycombinator.com