Implicit-structured representations causally effective
Trained networks can transform distributed representations of passive sentences into active voice and vice versa—exhibiting systematicity and showing that the implicit structure of their representations can be causally effective in processing.
David Chalmers (1990b).



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]
▲
The Connectionist Dilemma »The Connectionist Dilemma
▲
Connectionist representations avoid the dilemma »Connectionist representations avoid the dilemma
▲
Tensor product representations »Tensor product representations
▲
Constituents lack causal powers »Constituents lack causal powers
■
Implicit-structured representations causally effective
●
The RAAM network »The RAAM network
●
Chalmers's representations lack syntactic structure »Chalmers's representations lack syntactic structure
◄
David Chalmers »David Chalmers
+Komentarai (0)
+Citavimą (0)
+About