Intuition is the part of your knowledge that you cannot test for correctness. Proving correctness requires deriving a very low dimensional representation, so you can apply analytic operators. Most of the functions that a brain approximates cannot be translated into that form.
The problem of vision is quite similar to the problem of rendering. Computer graphics has figured out efficient models for most of that.
-
-
I would argue that our vision is not like 'inverse graphics'. The fidelity of rendering is unimportant. Rather, what is important is a rendering of a representation of the constraints in the space. The principle of least action tells us that only the most important is rendered.
-
We sample our space and recreate in our minds a rendering of the space. https://medium.com/intuitionmachine/ego-motion-in-self-aware-deep-learning-91457213cfc4 … We are intuitively aware of position, orientation, sequencing, composition and identity. That is what our brains capture.
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.