Re: Is generalisation a limit to intelligence?

From: Joaquim Almgren Gāndara (claw@lords.com)
Date: Sat Dec 02 2000 - 16:15:41 MST


> Leave that aside. Ben Goertzel clarified a part of Gandara's thesis that
> hadn't made any sense to me; e.g., that forced generalization may result
> in necessary creativity.

"Forced generalisation"? If by "forced" you mean that we need to generalise in
order to store and apply knowledge, then yes, that's what I meant.

> I had thought Gandara was proposing that perfect
> memory *prevented* generalization.

No, rather that perfect memory and an enormous processing capacity combined
would result in generalisations that defeat the purpose. I believe that all
generalisations with zero error (i.e. perfect classifications) are bad
generalisations, i.e. they suffer from overfitting. In addition, I suspect that
there is a point where a sentient being will have to choose either to suffer
from making less than perfect classifications or to suffer from overfitting.
Both paths lead away from my proposed upper limit to intelligence.

- Joaquim Gāndara
. claw@lords.com
. http://www.ite.mh.se/~joaal98
. http://games.scandit.com
. http://www.mp3.com/sdtank



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:35 MDT