From: Ben Goertzel (ben@goertzel.org)
Date: Thu Jun 13 2002 - 16:35:44 MDT
hi,
> Yes, if a deductive inference engine and symbolic knowledge representation
> repository were essential for Seed AI, then I agree that less than 20K
> lines of java code would be required, especially if a relational database
> were the object store.
A very nice, efficient, 1-machine AGI-friendly data representation framework
can be done in 5K-10K lines of C++.
You don't need to use an RDB to make this sort of thing compact. Of course,
Java bloats code compared to C++ ...
> My question to you then would be: Given a budget of 50K LOC, just what
> behaviors would you require the system to have? Or if your base system
> merely accepts knowledge for the next layer up, how many person-years of
> effort at that next layer would be required to achieve Seed AI, and what
> behaviors would be taught to the system with this budget.
I think a complete Novamente could be compressed into 50K lines of C++, at
significant cost in code comprehensibility and maintainability. Not a path
we're likely to take though, I'd prefer 200K lines of *good* code ;->
> Is reading important?
Reading should be learned, not wired-in. Ditto for nearly all linguistic
knowledge. However, cognitive mechanisms may be parameter-tuned for
performance on linguistic tasks. (e.g. logical unification may be tuned for
unification feature structure grammar parsing)
>What kinds of machine learning are required?
Probabilistic inference, but not Bayes-net-style, i.e. not assuming a global
pdf across all knowledge
Clustering
Evolutionary programming
>Does
> automated reasoning require justifications/explanations?
Sometimes yes, sometimes no. Producing these can slow inference down and is
not always contextually appropriate.
>What are the key
> attributes of a goal? ...
A goal is a predicate whose truth value indicates the extent to which it's
satisfied. Goals that are important are given lots of "oomph" ("importance"
in Novamente lingo) so that they can cause activity around themselves...
-- Ben
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:39 MDT