This kind of rapid cognitive development argues strongly (IMO) against the kind of experimental/experiential training that a tabula-rasa nn approach would indicate.
Human plasticity and logical reasoning are the apex of other processes and approaches, I think that because we have so much access (personally through introspection and socially via children) to models of theses processes, and the results are so spectacular and intrinsically impressive.
I used to go to the SAB conferences in the 90's, they're still going, but somewhat diminished I think. This was where the "Sussex School" of AI had it's largest expression - Phil Husbands, Maggie Boden and John Maynard Smith all spoke about the bridges between animal cognition and self organising systems. I am pretty sure that they were all barking up the wrong tree (he he he) but there was and is a lot of mileage in the approach.
I was just being glib about that. "Forever" is just hyperbole, but the 10+ some odd years it takes to go from birth to useful for most intellectual tasks is a pretty long-time in relative terms.
Brains must already have a lot of shortcuts built-in.
Oh absolutely. My point is just that there's no reason for us to not pursue "shortcuts" - as opposed to trying to build an ANN that's big enough to essentially replicate the actual mechanics of a real brain.
To extend this overall point though... it may be that as we learn newer/better algorithms and techniques we find out that you can actually make an ANN that would, for example, learn to do logical reasoning. And it might do so without need to use anywhere near the number of neurons and synapses that a real brain uses. But until such a time as it becomes apparent that this is likely, I think it's a good idea to continue researching "hybrid" systems that hard-wire in elements like various forms of symbolic/logical reasoning and anything else that we at least sorta/kinda understand.