http://www.cs.dartmouth.edu/~brd/Teaching/AI/Lectures/Summaries/natlang.html
To understand something is to transform it from one representation into another, where this latter representation is chosen to correspond to a set of available actions that could be performed, and for which a mapping is designed so that for each event an appropriate action will be performed.
My problem with "Compression/Compactness is Key to AI" or Occams razor is that it should be the upper bounding restriction, and not any base premise or Key to intelligence.
Using this principle we can make a "Better" intelligence, but NOT an intelligence, correct?
IE examples, if a procedure to boil an egg or such has 10 steps in it, but we have another that has 8 and they both achieve the goal correctly then we go with the shorter one.
But that sidesteps the entire problem of AI seeking, in that we have to Find/Learn both of those procedures First, and then the rest is simply optimization.
The same thought goes for Slow or Large AI's. They are both fine, once we show we can do one that is slow or is huge, then we can optimize it down to make it do it in real time space constraints.
Other:
A comment was made earlier about the types of learning as well, and one major thought was Consistency within the knowledge base, and this is one of the hardest things to achieve because to check consistency requires Already a full and knowedgable base to check against. So we are back to where does that initial base come from? Consistency checking against a partial database is notoriously bad due to missing incomplete information.
I think this is one point that we will have to substitute with the only intelligence we know, humans, and have them be the consistency checkers, in some easy simple wide scale fashion.
I am currently pondering a thought of a Wiki Style intelligence, or at least knowledge base. In the style of OpenMindCommonSense / Cyc / Wiki, by opening it up to a huge - user base, and putting a few restriction upon it. By this many things should be able to be learned about many common sense objects, and build up a base ontology as well.
James Ratcliff
Eric Baum <[EMAIL PROTECTED]> wrote:
Richard> Eric Baum wrote:
>>
Richard> Every step of the following argument begs questions and lacks
Richard> force:
>> If you want a more complete argument, read the book. One of the
>> reasons for writing a book is not to have to engage in arguments
>> piecemeal.
>>
>> Eric
Richard> I read your paper.
Richard> I am not sure how I would be helped by a "more complete"
Richard> version of an argument that already appears to be so severely
Richard> broken.
Richard> As I see it, the root cause of the trouble (in your paper, in
Richard> the literature behind that paper, and in the sequence of
Richard> arguments you summarized) is that some people have been so
Richard> obsessed with the idea of turning concepts like
Richard> "understanding" and "intelligence" into precisely formulated
Richard> concepts, amenable to mathematical proofs, that they are
Richard> willing to redefine and distort the meanings of those words
Richard> in order to strait-jacket them into the form they desire. In
Richard> this manner, you quote the COLT literature as having shown
Richard> that understanding is, essentially, compression.
My apologies for creating this misconception in your mind. The COLT
literature in no way claims that understanding is equivalent to
compression. It does not discuss understanding.
The COLT literature more or less proved that generalization in various
contexts is equivalent to finding hypotheses from simple classes.
Incidentally, these classes may or may not be viewed as compression,
one alternative criterion is finite VC-dimension (see chapter 4 of
WIT? for more details). There are also Bayesian viewpoints etc.
But in any case, these mathematical results mostly apply to prediction
of concepts, eg you see a series of pictures of chairs and not-chairs,
and desire to predict whether a new picture contains a chair or not.
The extrapolation to an explanation of understanding is mine,
so I bear whatever blame you may wish to assign.
This is where the distinction between exploiting structure and simply
finding a compact representation comes in. I am no longer talking
merely about finding a compact representation of some data, I am
extrapolating to a compact program that solves a variety of naturally
presented problems. It also is where mathematical proofs go out.
I would hope reading the book would give you a better appreciation
for why I think understanding comes from finding an Occam code.
I believe my book presents a straightforward explanation of what
understanding is and how it arises, that is consistent with all data
of which I'm aware, and which is very natural in the context of the COLT
results regarding concept generalization. I'm not aware of any
other theory of understanding that meets
these standards.
Richard> It is rather like taking the concept of "happiness" and
Richard> redefining it as "Happiness = A Warm Puppy". By doing this,
Richard> all of a sudden we have ways to measure happiness by
Richard> constructing a puppy density function, and we can further
Richard> refine it by measuring the temperature of the puppies, and
Richard> rating different puppies according their degree of puppiness.
Richard> This is great: we took the vague term "happiness" and
Richard> formalized it so nicely that now we can do math on the
Richard> happiness density field. Huge amounts of rigorous math can
Richard> follow from this, including precise - and very comforting -
Richard> proofs about the properties of this new "happiness".
Richard> Trouble is, its all BS. Not because the math is wrong (the
Richard> math is great!), but because the initial distortion of the
Richard> commonplace term was such an egregious distortion.
Richard> So it is with redefinitions of the term "understanding" to be
Richard> synonymous with a variety of compression. This is an
Richard> egregious distortion of the real meaning of the term, and
Richard> *everything* that follows from that distortion is just
Richard> nonsense.
Richard> Richard Loosemore.
Richard> Richard Loosemore
Richard> ----- This list is sponsored by AGIRI:
Richard> http://www.agiri.org/email To unsubscribe or change your
Richard> options, please go to:
Richard> http://v2.listbox.com/member/?list_id=303
-----
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/?list_id=303
_______________________________________
James Ratcliff - http://falazar.com
New Torrent Site, Has TV and Movie Downloads! http://www.falazar.com/projects/Torrents/tvtorrents_show.php
Everyone is raving about the all-new Yahoo! Mail beta.
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/?list_id=303
