@themattsimpson Yeah it seems like job #1 when going into the field would be to learn everything you can about stats, but apparently not
@davidmanheim @themattsimpson I haven’t seen any others that looked exciting, but maybe I missed something!
-
-
@Meaningness @themattsimpson I'd think the other obviously exciting application of deep learning and NNs is AlphaGo, right? -
@davidmanheim @themattsimpson Haven’t yet had time to read the AlphaGo paper, but my subjective probability that it’s meaningless is 0.94. - 3 more replies
New conversation -
-
-
@Meaningness @themattsimpson BTW, problem with SDT is that it SEEMS so obvious; just solve integrals to minimize loss chosen given priors. -
@Meaningness @themattsimpson (So people don't appreciate the power of the formulation.)
End of conversation
New conversation -
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.