AI is now largely concerned with the creation of models, with each model being specific to a single task. Human learning integrates everything into a single model of the same reality, which we call the universe. Unified learning is the most important open problem in AI.
-
-
Aha, ok. Cool! Is it right to say unified learning is then about developing a larger/more comprehensive and integrated model of the one domain/universe? What permits the difference in models between a human and a Narrow AI then? Is it at all to do with Frame Problems/Grounding?
-
The physical universe is a pattern generator. We learn to compress these patterns into a single unified model (res extensa), so we can predict observables. All other contents of our minds (hypotheticals, memories, intentions etc.) are res cogitans, and serve in our regulation.
- 2 more replies
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.