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 …
How many bits of innate knowledge do you think were accumulated in our evolutionary lineage, and what amount of data about our world would be required to extract the same amount of knowledge with principled statistical methods?
-
-
Not sure this kind of accounting is informative. The problem is that one way to construct a prior is to assemble a distribution, but I could also just change the support. Specifying the change in support is low bit cost, but incurs infinite KL divergence.
-
For example, in physics we assume 'physics does not change with time' - that excludes an infinite subset of possibilities from consideration (so its 'worth' infinite bits compared to uniform prior), but it doesn't take infinite bits to specify or learn.
- 7 more replies
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.