Re:Retrospective review of Gödel, Escher, Bach (1996) [pdf]
by dilyevsky on Tuesday March 30, 2021 @12:48AM
(#26631349)
A child’s model is also “pre-trained” by billions of years of evolution
[ Parent
| on HN ]
Re:Retrospective review of Gödel, Escher, Bach (1996) [pdf]
by fjfaase on Tuesday March 30, 2021 @05:10AM
(#26632517)
I understand that you put pre-trained between quotes, but I find it a little far fetched, because, as far as I understand, there is no evidence that any setting of the synpasis strength of certain neurons is transfered through DNA, it is only the organization of neurons, through layers and folds that is somehow encoded in the DNA. I also think that it is still a mystery why certain brain functions occur in certain areas of the brain.
Re:Retrospective review of Gödel, Escher, Bach (1996) [pdf]
by rubatuga on Tuesday March 30, 2021 @05:21AM
(#26632575)
That's still considered parameters of a generalized neural network.
Re:Retrospective review of Gödel, Escher, Bach (1996) [pdf]
by earthboundkid on Tuesday March 30, 2021 @07:25AM
(#26633311)
I think that has to be part of it, somehow, although I’m agnostic about whether it’s really analogous to “pretraining” an ML model. Whatever evolution was doing, it managed to give us neural nets that are mostly ready to go out of the box. Especially non-human animals often have short or no training periods.