>> I am extremely confident of Novamente's memory design regarding declarative
>> and procedural knowledge. Tweaking the system for optimal representation of
>> episodic knowledge may require some more thought.
Granted -- the memory design is very generic and will handle virtually
anything. The question is -- is it in a reasonably optimal from for retrieval
and other operations (i.e. optimal enough that it won't end up being impossibly
slow once you get a realistic amount of data/knowledge). Your caveat on
episodic knowledge proves very informative since *all* knowledge is effectively
episodic.
>> I have no idea what you mean by "scale invariance of knowledge" nor and only
>> weak understanding of what you mean by "ways of determining and exploiting
>> encapsulation and modularity of knowledge without killing useful "leaky"
>> abstractions."
Research project 1. How do you find analogies between neural networks,
enzyme kinetics and the formation of galaxies (hint: think Boltzmann)?
Research project 2. How do you recognize and package up all of the data that
represents horse and expose only that which is useful at a given time?
>> In terms of determining modularity of knowledge, NM seeks to do this via
>> various mechanisms, e.g.
>> -- pattern-mining using PLN, MOSES and clustering on the AtomTable, to
>> identify modularity of declarative knowledge within the existing knowledge
>> base
>> -- some specific program-tree-reduction heuristics to identify modularity
>> w/in populations of program trees ... i.e. mechanisms which focus on
>> procedural knowledge
These are all designed to operate on densely packed data of the same type, not
widely flung association networks. We're talking about widely differing
applications which mirror the difference between a discovery system and
something like, say, an analogy system.
>> Exploiting modularity of knowledge once it's identified is easier, because
>> modules once recognized may be explicitly represented as Atoms in the
>> AtomTable and as Combo nodes w/ in Combo program trees.
The "once it's identified" make the point moot. The question is -- how do you
recognize modules (see research project 2 above).
Novamente is great for what it does -- but I don't think that it's got the full
area of AGI covered yet.
-----
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?member_id=8660244&id_secret=64185471-22e82f
