Isn't this pointless? I mean, if I offer any proof you will just attack
the assumptions. Without assumptions, you can't even prove the universe
exists.
Just come up with decent assumptions that I'm willing to believe are likely.
I'm not attacking your assumptions just to be argumentative, I'm questioning
them because I believe that they are the root cause of your erroneous
"knowledge".
An AGI will have greater algorithmic complexity than the human brain
(assumption).
For example, it's very worthwhile to have you spell out something like this.
I don't believe that the AGI will have greater algorithmic complexity than
the human brain. It is my belief that after a certain point that *any*
intelligence can import and use any algorithm at need (given sufficient
time). Thus Legg's proof is irrelevant since any human given sufficient
time and knowledge will have sufficient algorithmic complexity to unravel
any AGI and any AGI given sufficient time and knowledge will have sufficient
algorithmic complexity to unravel any human. In the case of an AI
unraveling a human, however, I believe that the algorithmic complexity of a
human being is so ridiculously high (because each neuron is unique and
physically operates differently) that without being able to model down to
the lowest physical level that there *isn't* a level with lower algorithmic
complexity (i.e. low enough to be able for the AI to match). On the other
hand, I believe that the algorithmic complexity of an AGI can and will be
much lower.
Of course, I can't *prove* that last sentence but I can try to persuade you
that it is true by asking questions like:
1. Do you really believe that an average human requires more than a million
algorithms/recipes to do things (as opposed to a million applications of
algorithms to different data which is clearly a ridiculously low number)?
2. So -- How fast do humans learn algorithms and how many do they start
with hard-coded into the genome?
In your argument for transparency, you assume that individual pieces of
knowledge can be isolated. Prove it.
Yes, I do make that assumption but you've tacitly granted me that assumption
several times. Give me a counter-example of knowledge that can't be
isolated. My proof is that humans who truly possess a piece of knowledge
can always explain it (even if the explanation is only I've always seen it
happen that way). This is not the native representation of the knowledge
(neural networks) but is, nonetheless, a valid and transparent (and
isolated) representation.
In the brain, knowledge is distributed. We make decisions by integrating
many sources of evidence from all parts of the brain.
Yes. Neural networks do not isolate knowledge -- but that is a feature of
the networks, not the knowledge. I believe that *all* knowledge (or, at
least, the knowledge required to reach AGI-level intelligence can be
isolated/have their reasoning explained).
- - - -
To claim that knowledge can't be isolated is to claim that there is
knowledge that cannot be explained.
Do you want to
a) disagree with the above statement,
b) show me knowledge which can't be explained,
c) show why the statement is irrelevant, or
d) concede the point?
----- Original Message -----
From: "Matt Mahoney" <[EMAIL PROTECTED]>
To: <agi@v2.listbox.com>
Sent: Thursday, November 16, 2006 11:52 AM
Subject: Re: [agi] A question on the symbol-system hypothesis
Mark Waser <[EMAIL PROTECTED]>
wrote:
So *prove* to me why information theory forbids transparency of a knowledge
base.
Isn't this pointless? I mean, if I offer any proof you will just attack the
assumptions. Without assumptions, you can't even prove the universe exists.
I have already stated reasons why I believe this is true. An AGI will have
greater algorithmic complexity than the human brain (assumption).
Transparency implies that you can examine the knowledge base and
deterministically predict its output given some input (assumption about the
definition of transparency). Legg proved [1] that a Turing machine cannot
predict another machine of greater algorithmic complexity.
Aside from that, I can only give examples as supporting evidence.
1. The relative success of statistical language learning (opaque) compared
to structured knowledge, parsing, etc.
2. It would be (presumably) easier to explain human behavior by asking
questions than by examining neurons (assuming we had the technology to do
this).
In your argument for transparency, you assume that individual pieces of
knowledge can be isolated. Prove it. In the brain, knowledge is
distributed. We make decisions by integrating many sources of evidence from
all parts of the brain.
[1] Legg, Shane, (2006), Is There an Elegant Universal Theory of
Prediction?, Technical Report
IDSIA-12-06, IDSIA / USI-SUPSI, Dalle Molle
Institute for Artificial Intelligence, Galleria 2, 6928 Manno, Switzerland.
http://www.vetta.org/documents/IDSIA-12-06-1.pdf
-- Matt Mahoney, [EMAIL PROTECTED]
----- Original Message ----
From: Mark Waser <[EMAIL PROTECTED]>
To: agi@v2.listbox.com
Sent: Thursday, November 16, 2006 9:57:40 AM
Subject: Re: [agi] A question on the symbol-system hypothesis
> The knowledge base has high complexity. You can't debug it. You
can examine it and edit it but you can't verify its correctness.
While the knowledge base is complex, I disagree with the way in which
you're attempting to use the first sentence. The knowledge base *isn't* so
complex that it causes a truly insoluble problem. The true problem is that
the knowledge base will have a large enough size and will grow and change
quickly enough that you can't maintain 100% control over the contents or
even the integrity of it.
I disagree with the second but believe that it may just be your semantics
because of the third sentence. The question is what we mean by "debug".
If you mean remove all incorrect knowledge, then the answer is obviously
"yes, we can't remove all incorrect knowledge" because odd sequences of
observed events and incomplete knowledge means that globally incorrect
knowledge *is* the correct deduction from experience. On the other hand,
we certainly should be able to debug how the knowledge base operates, make
sure that it maintains an acceptable degree of internal integrity, and
responds correctly when it detects a major integrity problem. The
*process* and global behavior of the knowledge base is what is important
and it *can* be debugged. Minor mistakes and errors are just the cost of
being limited in an erratic world.
> An AGI with a correct learning algorithm might still behave badly.
No! An AGI with a correct learning algorithm may, through an odd sequence
of events and incomplete knowledge, come to an incorrect conclusion and
take an action that it would not have taken if it had perfect knowledge --
BUT -- this is entirely correct behavior, not bad behavior. Calling it bad
behavior dramatically obscures what you are trying to do.
> You can't examine the knowledge base to find out why.
No, no, no, no, NO! If you (or the AI) can't go back through the causal
chain and explain exactly why an action was taken, then you have created an
unsafe AI. A given action depends upon a small part of the knowledge base
(which may then depend upon ever larger sections in an ongoing pyramid) and
you can debug an action and see what lead to an action (that you believe is
incorrect but the AI believes is correct).
> You can't manipulate the knowledge base data to fix it.
Bull. You should be able to correctly come across a piece of incorrect
knowledge that lead to an incorrect decision. You should be able to find
the supporting knowledge structures. If the knowledge is truly incorrect,
you should be able to provide evidence/experiences to the AI that leads it
to correct the incorrect knowledge (or, you could just even just tack the
correct knowledge in the knowledge base, fix it so that it temporarily
can't be altered, and run your integrity repair routines -- which, I
contend, any AI that is going to go anywhere must have).
> At least you can't do these things any better than manipulating the
inputs and observing the outputs.
No. I can find structures in the knowledge base and alter them. I would
prefer not to. I would strongly prefer that it take the form of a
conversation where I "ask" the AGI what it's reasoning was, where it
answers, where I point out where I believe it's knowledge is incorrect and
provide proof, and where it can then alter its own knowledge base
appropriately.
> The reason is that the knowledge base is too complex. In theory you
could do these things if you lived long enough, but you won't. For
practical purposes, the AGI knowledge base is a black box.
No. I disagreed with your previous statement and I disagree with the
reason. The knowledge base is not that complex. It is that large. And
the AI should not be a black box *at all*. You should be able to examine
any given piece to any given level of detail at will -- you just can't hold
all of it in mind at once. Yes, that will lead to circumstances where it
surprises you -- but we're not looking for 100% predictability. We're
looking for an intelligence with *bounded* behavior.
> You need to design your goals, learning algorithm, data set and test
program with this in mind.
Prove to me that the AGI knowledge base is a black box and I will.
However, you have already told me that I "can examine it and edit it" --
so what the heck do *you* mean by a black box?
> Trying to build transparency into the data structure would be pointless.
Information theory forbids it.
Bull, information theory does not forbid transparency into the data
structure. Prove this and you would invalidate a huge swath of AGI
research. What makes you say this? I believe that this is the core of
your argument and would like to see *any* sort of evidence/argument to
support this grandiose claim.
> I am sure I won't convince you, so maybe you have a different
explanation why 50 years of building structured knowledge bases has not
worked, and what you think can be done about it?
Hmmm. Let's see . . . . Codd's paper was published in 1970, so the first
fifteen years were devoted to getting to that point. And SQL wasn't even
commercially available until Oracle was released in 1979, so we're down to
only about half that time. Cyc didn't start until 1984 after Machine
Learning started in the early 1980s. Many people took horrible detours
into neural networks while a lot of the rest were forced to constrain their
systems by the limited computing ability available to them (I remember
spending thousands of dollars per month running biochemistry simulations on
a Vax that I was able to easily run on a PC less than five years later).
In the past twenty years, people have continued to make financially-proven
progress in applications like genome databases.
It looks to me like 50 years of building structured knowledge bases has
worked and that were getting better at it all the time and also that we can
do more and more as space and computing power is getting cheaper and
cheaper and languages and techniques are getting more and more powerful.
What hasn't worked *yet* is self-structuring databases and we're learning
more all the time . . . .
So *prove* to me why information theory forbids transparency of a
knowledge base.
Mark
P.S. Yes, yes, I've seen that Google article before where the author
believes that he "proves" that "Google is currently storing multiple copies
of the entire web in RAM." Numerous debunking articles have also come out
including the facts that Google does not store HTML code, that what is
stored *is* stored in compressed form, and --from Google, itself -- that it
does *not* store sections that do not include "new instances of significant
terms". But I can certainly understand your personal knowledge base
deriving the "fact" that "Google DOES keep the searchable part of the
Internet in memory" if that article is all that you've seen on the topic
(though one would have hoped that an integrity check or a reality check
would have prompted further evaluation -- particularly since the article
itself mentions that that would require an unreasonably/impossibly large
amount of RAM.)
----- Original Message ----- From: "Matt Mahoney" <[EMAIL PROTECTED]>
To: <agi@v2.listbox.com>
Sent: Wednesday, November 15, 2006 6:41 PM
Subject: Re: [agi] A question on the symbol-system hypothesis
Mark Waser wrote:
Are you conceding that you can predict the results of a Google
search?
OK, you are right. You can type the same query twice. Or if you live long
enough you can do it the hard way. But you won't.
Are you now conceding that it is not true that "Models that are simple
enough to debug are too simple to scale."?
OK, you are right again. Plain text is a simple way to represent
knowledge. I can search and edit terabytes of it.
But this is not the point I wanted to make. I am sure I expressed it
badly. The point is there are two parts to AGI, a learning algorithm and a
knowledge base. The learning algorithm has low complexity. You can debug
it, meaning you can examine the internals to test it and verify it is
working the way you want. The knowledge base has high complexity. You
can't debug it. You can examine it and edit it but you can't verify its
correctness.
An AGI with a correct learning algorithm might still behave badly. You
can't examine the knowledge base to find out why. You can't manipulate the
knowledge base data to fix it. At least you can't do these things any
better than manipulating the inputs and observing the outputs. The reason
is that the knowledge base is too complex. In theory you could do these
things if you lived long enough, but you won't. For practical purposes,
the AGI knowledge base is a black box. You need to design your goals,
learning algorithm, data set and test program with this in mind. Trying to
build transparency into the data structure would be pointless. Information
theory forbids it. Opacity is not advantagous or desirable. It is just
unavoidable.
I am sure I won't convince you, so maybe you have a different explanation
why 50 years of building structured knowledge bases has not worked, and
what you think can be done about it?
And Google DOES keep the searchable part of the Internet in memory
http://blog.topix.net/archives/000011.html
because they have enough hardware to do it.
http://en.wikipedia.org/wiki/Supercomputer#Quasi-supercomputing
-- Matt Mahoney, [EMAIL PROTECTED]
-----
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
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
-----
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
-----
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