"i don't think it is! if groups of neurons that represent categories *stay* activated then a given speech act generates an entire volume in the conceptual manifold!"
-
-
i recommend pages 16, 37, and 40

-
pages 27-31 for phase a/synchronous binding :)
-
Andrea, I might have missed this -- have you tried implementing a "NOT" search operation? (by synchronously binding an undesirable attribute to a spare driven unit, so as to keep unwanted objects *out of phase* with wanted objects)
-
my first reaction was it could be implemented as a case of extreme asynchrony. I spoke with Alex, and in addition to this way I mentioned, he has thought about 3 other ways to implement it, one e.g. invert weights, we're happy to talk more about the other ways via email :)
-
thanks for thinking so much about the work with us
-
it's absolutely my pleasure. you're working on fundamental mechanisms needed for flexible, intelligent systems :D
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
interesting......... are the codes sub-symbolic?
