On probabilistic thinking and causality in deep learning systems https://medium.com/intuitionmachine/why-probability-theory-should-be-thrown-under-the-bus-36e5d69a34c9 …
-
Show this thread
-
Replying to @garybasin
Unfortunately the author seems to be a crank afaict
3 replies 0 retweets 1 like -
Replying to @Meaningness
crank detection: the ultimate test for intelligence
1 reply 0 retweets 1 like -
Replying to @garybasin
I bet that’s something DL would actually work well for! There are characteristic language tics cranks use.
1 reply 0 retweets 0 likes -
Replying to @Meaningness @garybasin
Non-equilibrium thermo is a classic crank trap. Sounds like it explains everything, but there’s basically nothing there
1 reply 0 retweets 2 likes -
Oh, totally, yeah! I’m offensively skeptical about Bayesianism as a general framework. (Good for some things ofc.)
2 replies 0 retweets 1 like
Replying to @Meaningness @Collinsjo12 and
I’m even more skeptical about non-eq thermo as an alternative tho. (But willing to have my mind changed…)
8:25 AM - 7 Nov 2017
1 reply
0 retweets
0 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.