The Past-Tense Acquisition Model
This implemented network model was trained to convert English phrases into the past tense. Although the network’s performance can be described by rules, no actual rules are utilised in its processing.
David Rumelhart & James McClelland (1986).

Note: More recent work along these lines includes that of Mark Seidenberg & James McClelland (1989).
Immediately related elementsHow this works
-
Artificial Intelligence »Artificial Intelligence
Can computers think? [1] »Can computers think? [1]
Yes: connectionist networks can think [5a] »Yes: connectionist networks can think [5a]
Connectionist networks can think without following rules »Connectionist networks can think without following rules
The Past-Tense Acquisition Model
Model doesn't argue against rule-based explanation »Model doesn't argue against rule-based explanation
David Rumelhart »David Rumelhart
James McClelland »James McClelland
+Kommentare (0)
+Verweise (0)
+About