Re: Is generalisation a limit to intelligence?

From: Joaquim Almgren Gāndara (
Date: Sat Dec 02 2000 - 12:31:09 MST

> Perhaps you're assuming that erroneousness itself adds some useful creative
> "noise" to the thought process, whereas a system with a good enough memory
> won't make enough errors to lead to creative thoughts. It's possible. Again,
> we lack the science to quantify this effect.

That's *exactly* what I mean. Thank you, sometimes I'm very bad with words. I
was trying to point out the trade-off between errors plus creative intelligence
and perfection plus rigid stupidity. Generalisation, as I see it, seems to be
necessary but also limiting.

> With memory limitations one is overfitting to an even smaller subset of the
> data than is necessary.

Ah, I see what you mean.

> IN a data-rich situation, more memory decreases the severity of overfitting,
> in general.

This, however, I don't understand. Do you mean that overfitting itself decreases
as the set of data increases, or that overfitting to a large data set is OK? If
you mean the former, it seems to me that an AI with infinite capacity and finite
knowledge will always suffer from overfitting and thus be too rigid and not
really intelligent at all (although it might fool most people, what with its
infinite capacity and all). If you mean the latter, I don't think I understand
how overfitting can be a good thing.

- Joaquim Gāndara

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