I'm starting to learn about Numenta's HTM, but perhaps someone would
like to share in advance:
what are the essential differences between HTM and Yuang Weng's IHDR
augmented with Observation-driven MDPs?
-
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change
Ouch, they differ more than I thought... Good :-)
(HTM based more on Bayes nets)
On 6/24/07, Lukasz Stafiniak [EMAIL PROTECTED] wrote:
I'm starting to learn about Numenta's HTM, but perhaps someone would
like to share in advance:
what are the essential differences between HTM and Yuang Weng's
Pei Wang wrote:
Hi,
I put a brief introduction to AGI at
http://nars.wang.googlepages.com/AGI-Intro.htm , including an AGI
Overview followed by Representative AGI Projects.
This looks pretty good to me. My compliments.
(And now the inevitable however...)
However, the distinction you
I have one of Richard Sutton's books, and RL methods are useful but I
also have some reservations about them. Often in this sort of
approach a strict behaviorist position is adopted where the system is
simply trying to find an appropriate function mapping inputs to
outputs. The internals of the
Understood. The distinction isn't explained in the short introduction
at all, and that is why I linked to my paper
http://nars.wang.googlepages.com/wang.AI_Definitions.pdf , which
explains it in a semi-formal manner.
Pei
On 6/24/07, Eliezer S. Yudkowsky [EMAIL PROTECTED] wrote:
Pei Wang wrote:
One conceptual difference is that BN corresponds to a third person
viewpoint on probable relations among events, while MDP corresponds to
a first person viewpoint on probable relations between actions and
consequences.
Pei
On 6/24/07, Bo Morgan [EMAIL PROTECTED] wrote:
My understanding is
On 6/24/07, Bob Mottram [EMAIL PROTECTED] wrote:
I have one of Richard Sutton's books, and RL methods are useful but I
also have some reservations about them. Often in this sort of
approach a strict behaviorist position is adopted where the system is
simply trying to find an appropriate
The obvious observation is that HTM is bottom-up and IHDR is top-down.
HTM builds hierarchy by merging fixed, topologically-organized,
coordinate-system-based subspaces: tilings, where IHDR builds
hierarchy by splitting input space by adaptively learned Gaussian
features.
-
This list is