As far as current machine learning is concerned, generalization originates from the ability to learn the latent manifold on which the training data lies, i.e. the ability to interpolate between training samples (local generalization, by definition)
-
-
Of course, interpolation & pattern recognition are nevertheless a fundamental component of intelligence -- just not the most powerful. Being able to do it well -- by refining deep learning -- is immensely valuable
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It won't be able to extrapolate non-linearly.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
AGI for any type of intelligence or only analytical ? :-)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Would “thinking outside the box” be a fair metaphor ? Of course, just because you are thinking outside of a particular box doesn’t mean you’re not still within a larger box, IOW: how general would that general intelligence be?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.