Thinking about differences in terms of building instructions is fruitless surely. I could make a hugely complex structure with only a few lines of code and dont get me started on bootstrapping which adds even more to the emergent complexity.
-
-
Psychologists call this stuff "motivation"; it' part of the answer, but inot the whole answer. What I don't understand is why some folks are comfortable ascribing fairly detailed innate structure to motivations (or loss functions) but not to other aspects of cognition.
-
I’m comfortable ascribing innate structure to a ton else. But loss functions are nice and compact, and we know there is learning... so what I’m less comfortable with is AI people using too-generic and math-y end to end losses rather than diverse ethologically specific losses.
- 8 more replies
New conversation -
-
-
And to get birds, yeah, you need a whole sequence of super specific reward or loss functions to shape different parts of the brain at different times, and activating on cue from the environment. Very much like this maybe (in birds!):https://www.nature.com/articles/s41598-018-25112-5 …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.