The solid proposal is that we need to search a different part of model space, as described in detail in 2001, where I made several specifics proposals about important challenges that the ML community simply has refused (for the most part) to engage with. I can't do it on my own.
-
But there is no specific proposal for a model that has those desiderata! <--This is precisely the point. What you perceive as lack of engagement is me trying to get us to stop talking past each other and actually talk about a solution. Desired properties != solution
i figured you wouldn’t engage in the desiderata and would again try to turn things around. if you can’t understand why clear desiderata are important and can’t engage in whether a set of desiderata makes sense, there is zero point in continuing this discussion.
-
-
I'm truly, genuinely puzzled. Why does my opinion on the validity of those desiderata in any way inform your proposed model solution that satisfies them? I can disagree with whether they are necessary or sufficient and still acknowledge whether a model satisfies them.
-
you seem almost literally blind to the value of desiderata and of knowing the limits on a particular framework; you can’t stop talking about whole models (none yet adequate) long enough to see the important prerequisites along the way. i honestly don’t know how to help you.
End of conversation
New conversation -
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.