Seems to. A big lesson of recent machine learning is that vast training sets can often compensate for suboptimally-designed networks.
The bigger the neural network, the more it overfits the training data. The bigger the government, the more it overfits the current culture.pic.twitter.com/7mCGZfHsb8
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Make the joke bro.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
All else equal, it's generally true, esp with too many nodes per layer and too small a training set.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Get rid of the Dept of Education? ;)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
We could just drop everything that's not allowed in the Constitution, for a start...
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Kropotkin had interesting ideas that influenced multilevel/group selection theory, which I have no problem with (see Ch. 9 of Mating Mind)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Sociobiology was a useful 1970s precursor to 1990s evo psych, but it didn't model psychological adaptations in as much empirical detail.
-
I sometimes wonder if evo psych is just a footnote to Trivers.
End of conversation
New conversation -
-
-
Getting rid of government portion of gdp and using the rest as the real metric of well being.
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.