A very fuzzy explanation. I love it. It is perfect for the world of uncertainty and cats in superposition. ML leads to entanglement. God help us all!
A critique of ML you sometimes hear from non-ML people is that ML, unlike Physics, lacks certainty, precision, and exactitude. That is by necessity: ML is a fuzzy way to deal with fuzzy problems.
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
To be fair, there is some work on learning crisp categories, rules, programs etc. using probabilistic ("fuzzy") reasoning. Tenenbaum lab etc.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This is incredibly reductive. There’s more to ML than methods involving continuous values.
-
Also Physics is known to use continuous functions every now and then. (In fact in Physics every Taylor series converges :D)
- Show replies
New conversation -
-
-
If physics
could have solved those types of problems, it would have already.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It’s still early.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It's part of what I loved about ML. I had massively fuzzy problems to solve back in ~2000. ML gave me tools to bracket the fuzziness and find useful roots.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This is a common criticism from people with little background in statistics. People often criticize economics for the same reason. The whole school of Austrian economics seems to say econometrics is useless because the R^2<1.
-
... and they are 100% correct.
End of conversation
New conversation -
-
-
Even in physics, most practical problems lack analytical solutions and numerical methods are employed that too lack exactitude and involve approximations. I think providing uncertainty estimates too, and not just point estimates, is necessary for both ML and numerical methods.
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.