Generality in AI (which a matter of degree, not an absolute) is an v. important problem. Yet, strangely, the people who say they work on "AGI" don't seem to be interested in understanding the problem of generality, & instead focus on achieving task-specific skill by scaling up DL
-
-
Which current sub field of ML do you find most promising for generality? My intuition would be Reinforcement Learning and Genetic Algorithms, because they don’t require human labeled data to build. But they do suffer acutely from task specificity as well..
-
Flexible and broad AI will come from a combination of techniques, including pattern recognition. I see program synthesis and in particular genetic programming as holding potential. But really, we should explore more.
- Show 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.