I’ve been skeptical about DL results because 25 years ago I reran the key experiments that were hyped as showing backprop (the underlying tech) was incredible. In each case I found that the researchers were fooling themselves. Not deliberate fraud, but sloppy work.
-
-
Show this thread
-
There’s a pervasive culture in ML research of competing to prove your method can do magic, instead of trying to understand what’s going on. Systematic failure to ask skeptical questions, or to do the necessary control experiments.
Show this thread
End of conversation
New conversation -
-
-
You're right to flag this up. Supervised learning approaches, like neural nets, genetic algos, and support vector machines all tune towards a "right" answer, baking in the prejudices of whoever makes the call. Beware black boxes, parameters, and "fitting"!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.