I believe the company mentioned in this article was referenced in an active
thread here recently. They claim to have semantically enabled Wikipedia.
Their stuff is supposed to have a vocabulary 10x that of the typical
U.S. college graduate. Currently being licensed to software developers
On Sat, Sep 20, 2008 at 4:37 PM, Brad Paulsen [EMAIL PROTECTED] wrote:
Oh, OK, so I added the stuff in the parentheses. Sue me.
Hehe, indeed. Although I'm sure Powerset has some nice little
relationship links between words, I'm a little skeptical about the
claim to meaning. I don't mean that
The lectures are pretty good in quality, compared with other major
university on-line lectures (such as MIT and so forth) I followed a couple
of them and definitely recommend. You learn almost as much as in a real
course.
On Thu, Sep 18, 2008 at 2:19 AM, Kingma, D.P. [EMAIL PROTECTED] wrote:
Hi
Matt,
So, what formal language model can solve this problem?
A FL that clearly separates basic semantic concepts like objects,
attributes, time, space, actions, roles, relationships, etc + core
subjective concepts e.g. want, need, feel, aware, believe, expect,
unreal/fantasy. Humans have senses
On Fri, Sep 19, 2008 at 10:05 PM, Matt Mahoney wrote:
From http://en.wikipedia.org/wiki/Yeltsin
Boris Yeltsin studied at Pushkin High School in Berezniki in Perm Krai. He
was fond of sports (in particular
skiing, gymnastics, volleyball, track and field, boxing and wrestling)
despite losing
2008/9/20 Valentina Poletti [EMAIL PROTECTED]:
The lectures are pretty good in quality, compared with other major
university on-line lectures (such as MIT and so forth) I followed a couple
of them and definitely recommend. You learn almost as much as in a real
course.
The introduction to
On Fri, Sep 19, 2008 at 11:46 PM, Matt Mahoney [EMAIL PROTECTED] wrote:
So perhaps someone can explain why we need formal knowledge representations
to reason in AI.
Because the biggest open sub problem right now is dealing with
procedural, as opposed to merely declarative or reflexive,
It has been mentioned several times on this list that NARS has no
proper probabilistic interpretation. But, I think I have found one
that works OK. Not perfectly. There are some differences, but the
similarity is striking (at least to me).
I imagine that what I have come up with is not too
Mike,
On 9/19/08, Mike Tintner [EMAIL PROTECTED] wrote:
Steve: Thanks for wringing my thoughts out. Can you twist a little
tighter?!
A v. loose practical analogy is mindmaps - it was obviously better for
Buzan to develop a sub-discipline/technique 1st, and a program later.
MAJOR
On Saturday 20 September 2008, Trent Waddington wrote:
Hehe, indeed. Although I'm sure Powerset has some nice little
relationship links between words, I'm a little skeptical about the
claim to meaning. I don't mean that in a philosophical not
grounded sense.. I'm of the belief that you
Steve:
If I were selling a technique like Buzan then I would agree. However, someone
selling a tool to merge ALL techniques is in a different situation, with a
knowledge engine to sell.
The difference AFAICT is that Buzan had an *idea* - don't organize your
thoughts about a subject in random
Abram,
I think the best place to start, in exploring the relation between NARS
and probablity theory, is with Definition 3.7 in the paper
From Inheritance Relation to Non-Axiomatic
Logichttp://www.cogsci.indiana.edu/pub/wang.inheritance_nal.ps
[*International Journal of Approximate
Convergence08 http://www.convergence08.org.
Join a historic convergence of leading long term organizations and thought
leaders. Two days with people at the forefront of world-changing
technologies that may reshape our career, body and mind – that challenge our
perception of what can and should
--- On Fri, 9/19/08, Jan Klauck [EMAIL PROTECTED] wrote:
Formal logic doesn't scale up very well in humans. That's why this
kind of reasoning is so unpopular. Our capacities are that
small and we connect to other human entities for a kind of
distributed problem solving. Logic is just a tool
On Sat, Sep 20, 2008 at 4:44 PM, Matt Mahoney [EMAIL PROTECTED] wrote:
--- On Fri, 9/19/08, Jan Klauck [EMAIL PROTECTED] wrote:
Formal logic doesn't scale up very well in humans. That's why this
kind of reasoning is so unpopular. Our capacities are that
small and we connect to other human
Ben,
Thanks for the references. I do not have any particularly good reason
for trying to do this, but it is a fun exercise and I find myself
making the attempt every so often :).
I haven't read the PLN book yet (though I downloaded a copy, thanks!),
but at present I don't see why term
I haven't read the PLN book yet (though I downloaded a copy, thanks!),
but at present I don't see why term probabilities are needed... unless
inheritance relations A inh B are interpreted as conditional
probabilities A given B. I am not interpreting them that way-- I am
just treating
And the definition 3.7 that you mentioned *does* match up, perfectly,
when the {w+, w} truth-value is interpreted as a way of representing
the likelihood density function of the prob_inh. Easy! The challenge
is section 4.4 in the paper you reference: syllogisms. The way
evidence is spread
BTW, University of Washington has free grad computer science course
videos, including a couple AI courses:
http://www.cs.washington.edu/education/dl/course_index.html
My personal favorite is the data mining course by Pedro Domingos:
http://www.cs.washington.edu/education/courses/csep573/01sp/
On Sat, Sep 20, 2008 at 6:24 PM, Matt Mahoney [EMAIL PROTECTED] wrote:
--- On Sat, 9/20/08, Ben Goertzel [EMAIL PROTECTED] wrote:
If formal reasoning were a solved problem in AI, then we would have
theorem-provers that could prove deep, complex theorems unassisted. We
don't. This indicates
Well, one question is whether you want to be able to do inference like
A --B tv1
|-
B --A tv2
Doing that without term probabilities is pretty hard...
Not the way I set it up. A--B is not the conditional probability
P(B|A), but it *is* a conditional probability, so the normal Bayesian
On Sat, Sep 20, 2008 at 2:22 PM, Abram Demski [EMAIL PROTECTED] wrote:
It has been mentioned several times on this list that NARS has no
proper probabilistic interpretation. But, I think I have found one
that works OK. Not perfectly. There are some differences, but the
similarity is striking
-- Matt Mahoney, [EMAIL PROTECTED]
--- On Sat, 9/20/08, Ben Goertzel [EMAIL PROTECTED] wrote:
It seems a big stretch to me to call theorem-proving guidance a language
modeling problem ... one may be able to make sense of this statement, but
only by treating the concept of language VERY
Beside the problem you mentioned, there are other issues. Let me start
at the basic ones:
(1) In probability theory, an event E has a constant probability P(E)
(which can be unknown). Given the assumption of insufficient knowledge
and resources, in NARS P(A--B) would change over time, when
Matt,
I really hope NARS can be simplified, but until you give me the
details, such as how to calculate the truth value in your converse
rule, I cannot see how you can do the same things with a simpler
design.
NARS has this conversion rule, which, with the deduction rule, can
replace
Thanks for the critique. Replies follow...
On Sat, Sep 20, 2008 at 8:20 PM, Pei Wang [EMAIL PROTECTED] wrote:
On Sat, Sep 20, 2008 at 2:22 PM, Abram Demski [EMAIL PROTECTED] wrote:
[...]
The key, therefore, is whether NARS can be FULLY treated as an
application of probability theory, by
To pursue an overused metaphor, to me that's sort of like trying to
understand flight by carefully studying the most effective high-jumpers.
OK, you might learn something, but you're not getting at the crux of the
problem...
A more appropriate metaphor is that text compression is the
(2) For the same reason, in NARS a statement might get different
probability attached, when derived from different evidence.
Probability theory does not have a general rule to handle
inconsistency within a probability distribution.
The same statement holds for PLN, right?
PLN handles
On Sat, Sep 20, 2008 at 9:09 PM, Abram Demski [EMAIL PROTECTED] wrote:
(1) In probability theory, an event E has a constant probability P(E)
(which can be unknown). Given the assumption of insufficient knowledge
and resources, in NARS P(A--B) would change over time, when more and
more
Think about a concrete example: if from one source the system gets
P(A--B) = 0.9, and P(P(A--B) = 0.9) = 0.5, while from another source
P(A--B) = 0.2, and P(P(A--B) = 0.2) = 0.7, then what will be the
conclusion when the two sources are considered together?
There are many approaches to
Pei:In a broad sense, formal logic is nothing but
domain-independent and justifiable data manipulation schemes. I
haven't seen any argument for why AI cannot be achieved by
implementing that
Have you provided a single argument as to how logic *can* achieve AI - or
to be more precise,
I didn't know this paper, but I do know approaches based on the
principle of maximum/optimum entropy. They usually requires much more
information (or assumptions) than what is given in the following
example.
I'd be interested to know what the solution they will suggest for such
a situation.
Pei
The approach in that paper doesn't require any special assumptions, and
could be applied to your example, but I don't have time to write up an
explanation of how to do the calculations ... you'll have to read the paper
yourself if you're curious ;-)
That approach is not implemented in PLN right
I found the paper.
As I guessed, their update operator is defined on the whole
probability distribution function, rather than on a single probability
value of an event. I don't think it is practical for AGI --- we cannot
afford the time to re-evaluate every belief on each piece of new
evidence.
You are right in what you say about (1). The truth is, my analysis is
meant to apply to NARS operating with unrestricted time and memory
resources (which of course is not the point of NARS!). So, the
question is whether NARS approaches a probability calculation as it is
given more time to use all
Ben: Mike:
(And can you provide an example of a single surprising metaphor or analogy
that have ever been derived logically? Jiri said he could - but didn't.)
It's a bad question -- one could derive surprising metaphors or analogies by
random search, and that wouldn't prove anything
On Sat, Sep 20, 2008 at 11:02 PM, Abram Demski [EMAIL PROTECTED] wrote:
You are right in what you say about (1). The truth is, my analysis is
meant to apply to NARS operating with unrestricted time and memory
resources (which of course is not the point of NARS!). So, the
question is whether
On Sat, Sep 20, 2008 at 10:32 PM, Pei Wang [EMAIL PROTECTED] wrote:
I found the paper.
As I guessed, their update operator is defined on the whole
probability distribution function, rather than on a single probability
value of an event. I don't think it is practical for AGI --- we cannot
Mike,
I understand that my task is to create an AGI system, and I'm working on
it ...
The fact that my in-development, partial AGI system has not yet demonstrated
advanced intelligence, does not imply that it will not do so once completed.
No, my AGI system has not yet discovered surprising
and not to forget...
SATAN GUIDES US TELEPATHICLY THROUGH RECTAL THERMOMETERS. WHY DO YOU THINK
ABOUT META-REASONING?
On Sat, Sep 20, 2008 at 11:38 PM, Ben Goertzel [EMAIL PROTECTED] wrote:
Mike,
I understand that my task is to create an AGI system, and I'm working on
it ...
The fact
Ben,
Not one metaphor below works.
You have in effect accepted the task of providing a philosophy and explanation
of your AGI and your logic - you have produced a great deal of such stuff
(quite correctly). But none of it includes the slightest explanation of how
logic can produce AGI - or,
Mike
If you want an explanation of why I think my AGI system will work, please
see
http://opencog.org/wiki/OpenCogPrime:WikiBook
The argument is complex and technical and it would not be a good use of my
time to recapitulate it via email!!
Personally I do think the metaphor
COWS FLY LIKE
Ben, Just to be clear, when I said no argument re how logic will produce
AGI.. I meant, of course, as per the previous posts, ..how logic will
[surprisingly] cross domains etc. That, for me, is the defining characteristic
of AGI. All the rest is narrow AI.
43 matches
Mail list logo