Math is a tool, a language of sorts. Having a math background does not magically allow to "understand" anything, and in particular not ML.
-
Math merely provides you with one way to formally reason about ML. But to reason about it, you must first understand it.
And math will not do the understanding for you. If it did, mathematicians would dominate the field of ML, which they most definitely do not.
-
-
In my experience, physicists tend to convert to ML more easily than people from a math or stats background. Interesting to note.
-
Would you say the same principle applies to discovery of new methods? Obviously plenty of overlapping concepts (LI, Complex, etc)
End of conversation
New conversation -
-
-
"heuristically" is not a mathematicians' favorite word.
-
.
@fchollet math proofs can provide useful intuition in#MachineLearning.
End of conversation
New conversation -
-
-
what you say is quite ironic because mathematics (μαθηματικά) actually means "things about learning".
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.