The compression approach is essentially a bottom-up,
clustering algorithm whose objective is to form high-level
concepts. I'm wondering if something analogous may be
formulated in the reverse direction, ie going from high level
concepts to low level representations. Maybe this is the
The compression approach is essentially a bottom-up,
clustering algorithm whose objective is to form high-level
concepts. I'm wondering if something analogous may be
formulated in the reverse direction, ie going from high level
concepts to low level representations. Maybe this is the
Hi,
In my compression-based design, the concepts formed by
compression are unlabeled. For example, in a fruits world
there would be concepts for apples, oranges and bananas. My
question is how may Novamente make use of the concepts formed
using my method. It would be a nice thing if
However, I think that the spontaneous emergence of complex concepts like
prepositional ones from sensory inputs is not very practical, and will
take an insane amount of compute time to occur, even though it's
possible.
I think that, in practice, we'll need to use a combination of explicit
I'm still trying to see if my compression-based AGI is
feasible. I think the first experiment would be to implement
a kind of generic memory that can store arbitrary items.
Just wondering if other groups may be interested in using
this module in their AGI...
YKY
In my approach to
