Re:The Principles of Deep Learning Theory
by mjburgess on Sunday April 17, 2022 @04:31AM
(#31059445)
If you have all possible ways of measuring the world, and all possible measurements you can produce all possible models. A subset of those models will be appear relevantly intelligent.
But that isnt intelligence. Intelligence is the solution to the problem of those "all possibles" being imposssible. Namely, intelligence is how animal's conduct themselves in the face of not knowing what the data is..
they do this by conducting themselves and their bodies in their environment -- they dont focus on the problem in the AI/ML/etc. sense... In this way they dont make decisions based on "data" -- they move according to self-regulatory goals.
The data which they encounter, in that movement, becomes useful for reasoning about the world. But its radically more accidental, partial, and speculative than ML requires.
Isn't there an implicit conclusion here that the extra dimensions of 'world being' would actually make the manifold hypothesis true, it's just missing data in the training model? Not to say it's trivial to fix, that missing data might be derived laws of physics, smell, shared world models of a society etc. but none the less I fail to see how conceptually any of that couldn't be reduced to data.