bwhite at oucsace.cs.ohiou.edu (William E. White ) writes...
>In the process of investigating "self-training" models, I learned about
>ART networks; however I found one potential problem which I wanted to ask
>about. It occurs to me that, while the vigilance of the network can vary
>depending on success or failure, it varies "globally". However, it seems
>that human vigilance varies "locally"; for example, a person among one
>race of people finds it easier to distinguish people of that race than
>of others. Similar examples can be drawn, I'm sure.
>What this amounts to is that there needs to be a way of disambiguating
>closely-related but different stimuli, while still correctly categorizing
>noisy, far-related stimuli. ART seems unable to do this.
>Is there currently any self-training model, derived either from biological
>research or from AI, which provides for this? The only thing that I could
>think of was inserting layers between F1 and F2 which would selectively
>disambiguate, but then we're back to the problem of how to train them.
I vaguely recall that former immunologist Gerald Edelman was working on a
model of category vigilance based on his theory of neural selection. I don't
have the cites with me, though. Don't know how far he got with it, either.
kind regards,
todd
+-----------------------------------------------------------------------------+
| Todd I. Stark stark at dwovax.enet.dec.com |
| Digital Equipment Corporation (215) 542-3573 |
| Philadelphia, Pa. USA |
| "(A word is) the skin of a living thought" Oliver Wendell Holmes, Jr. |
+-----------------------------------------------------------------------------+
