Conscious rule-interpreter can elaborate its capacities
The one-trial learning process McCarthy describes is carried out by a conscious rule-interpreter, which learns and applies new rules immediately—comparatively slowly—and then encodes them in the weights of the intuitive processor—comparatively fast.
How the conscious rule-interpreter would change its weights for one-trial learning is the subject of current research.

Paul Smolensky, 1988b.
PAGE NAVIGATOR(Help)
-
Artificial Intelligence »Artificial Intelligence
Can computers think? [1] »Can computers think? [1]
Yes: connectionist networks can think [5a] »Yes: connectionist networks can think [5a]
The Subsymbolic Paradigm »The Subsymbolic Paradigm
Connectionist networks can’t elaborate capacities quickly »Connectionist networks can’t elaborate capacities quickly
Conscious rule-interpreter can elaborate its capacities
+Commentaar (0)
+Citaten (0)
+About