Constituents lack causal powers
The parts of a tensor product representation are not explicitly contained or "tokened" within it—the parts have no independent status in the complex representation. As such, tensor product constituents lack individual causal powers.
Classical constituents by contrast, have causal powers by virtue of being explicitly contained in complex representations.

Jerry Fodor & Brian McLaughlin (1990).
CONTEXT(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 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
●
Implicit-structured representations causally effective »Implicit-structured representations causally effective
●
Nonclassical constituents can be causally effective »Nonclassical constituents can be causally effective
◄
Jerry Fodor »Jerry Fodor
+Comments (0)
+Citations (0)
+About