As you can see in the comments you are confusing the audience. But to your argument: why do you think that the priors can be found by organic evolution but not by any other statistical search method?
Of course, evolution is statistical. But as I wrote in AlphaGo critique: blurring distinction between evolution & learning blurs causal mechanisms. May as well call it all change and lump rock formation with classical conditioning; key question is whether you need strong priors.https://twitter.com/plinz/status/968490295968063488 …
-
-
- 8 more replies
New conversation -
-
-
Calling evolution 'statistical' seems rather instrumentalist. To make predictions we use statistical models and methods, but to explain it, they are not required.
- 1 more reply
New conversation -
-
-
And where the priors come from
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Seem clear to me there is an effort to rationalize AI disconnected from their human creators and human data generators. To make AI to be something it never will be. Why? Bow down to the stone image ruler over you but ignore the humans behind the biased curtain controlling the AI.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Do you think evolutionary algorithms learn things that non-evolutionary algorithms can’t? That seems important for nature/nature debate
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I think the causal distinction doesn't differentiate learning from non-learning (taking "learning", I think uncontroversially, to be persistent behavioural changes due to environmental input). Difference is maybe timescale related (or maybe individual vs population level?)...
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
"May as well call it all change" -- I wish to pause an think about it: Fundamental physics does not know where it ends, and biology or psychology begins. It all always is a physical dynamics of the universe, in which, for whatever complex reasons, some modes grow stronger.
-
The peculiar thing, is, of course, how simple this unfathomably complex dynamics can become when coarse grained -- not only do atoms always interact in a certain way with other atoms, but so do enormous lumps of atoms that are cats, etc.
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.