All models are wrong. Some models are useful. Gluing together just the useful bits of a bunch of models produces a Franken-model that is less wrong. Welcome to the age of evolved splines.
-
-
-
I don't yet understand why all models are wrong. Models of mathematics are surprisingly often correct, and every implementation must have a ground truth, to which a model can in principle often be isomorphic.
- 2 more replies
New conversation -
-
-
What are conceivable computations that brains have, but DL does not? The most salient one seems to be coincidence detection (spatio-temporal clustering): https://neurophysics.ucsd.edu/courses/physics_171/annurev.neuro.28.061604.135703.pdf …
-
Also one-shot learning seems to be crucial. Much of human cognition seems to be based on jumping between and thereby combining one-shot learned attractor states that encode short sequences (~.1-10 seconds). The strategy of combining itself seems to be largely one-shot learned.
- 1 more reply
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.