Neocortical Architectures

John Snodgrass snodgras at crash.cts.com
Wed Dec 22 17:43:48 EST 1993


In <2f9h8j$pfe at wp-sp.nba.TRW.COM> erwin at trwacs.fp.trw.com (Harry Erwin) writes:

[...]
>The weakness of a system designed this way is that attention in each layer
>is controlled by the layer below it. Eventually, this regression of
>control peters out

      You don't know this, you assume it. After this, your model
is useless, you are fraught with endless complexities. Look at the
evidence for a finite regression.

      JES




More information about the Neur-sci mailing list