"Either than or the noise is a regularization, and they aren’t getting a quantum benefit but more like a dropout boost."
Ha. I knew I posted to the right channel. I wouldn't have been able to catch that, though I would have imagined various classical regularization parameter sweeps would have been part of the fine-tuning of their null model. I'm still trying to wrap my head around what the quantum data transform is supposed to buy, is it effectively a preprocessor for a classical learning model?
.- .-.. .-.. / ..-. --- --- - . .-. ... / .- .-. . / .-- .-. --- -. --. / ... --- -- . / .- .-. . / ..- ... . ..-. ..- .-.. FRIAM Applied Complexity Group listserv Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom https://bit.ly/virtualfriam to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com FRIAM-COMIC http://friam-comic.blogspot.com/ archives: 5/2017 thru present https://redfish.com/pipermail/friam_redfish.com/ 1/2003 thru 6/2021 http://friam.383.s1.nabble.com/
