The RAAM network
Passive-active transformations can be achieved in part , via a recursive auto-associative memory (RAAM) network (see detailed text).
A RAAM network compresses constituent vectors into complex representations, and decompresses those complex representations back into their constituent parts.

Processes of compression and decompression can be repeated to deal with arbitrarily complex connectionist representations.



John Pollock, 1990.
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 »Implicit-structured representations causally effective
■
The RAAM network
+Commentaires (0)
+Citations (0)
+About