I would argue biological evolution is Not a form of statistical learning - since there is no learning - but pure selection, among random changes in the genomic code and interaction of biomolecules, completely determined by specific dependencies/constraints of the environment.
-
-
-
Learning is the search for better function approximations, and so is evolution. Gradient descent works only when you can identify a gradient. Otherwise you are stuck with evolutionary methods.
- 14 more replies
New conversation -
-
-
Evolution, itself, may have statistical facets, but FITNESS is not statistical - fitness requires functional analysis. Someone needs to study computational irreducibility.
-
Evolutionary fitness of multicellular organisms is a noisy loss function that has a very pronounced local optimum for general intelligence.
End of conversation
New conversation -
-
This Tweet is unavailable.
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.