Generality in AI (which a matter of degree, not an absolute) is an v. important problem. Yet, strangely, the people who say they work on "AGI" don't seem to be interested in understanding the problem of generality, & instead focus on achieving task-specific skill by scaling up DL
-
-
Program synthesis seems so far from biology that it's hard to believe it would be a huge help, but then again helicopters have rotors
-
Marcos -- our blog and the attached paper "cognitive programs" has cognitive science and neuroscience references that might be of interest to you. https://www.vicarious.com/2019/01/18/a-thought-is-a-program/ …
End of conversation
New conversation -
-
-
Hey
@fchollet, I'm really interested in program synthesis, do you know of any research groups working on this?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.