IMatt,
I mainly want to lay down a marker here for a future discussion.
What you have done is what all AGI-ers/AI-ers do. Faced with the problem of
domain-switching - (I pointed out that the human brain and human thought are *
freely domain-switching*), - you have simply ignored it - and, I imagine, are
completely unaware that you have done so. And this, remember, is *the* problem
of AGI - what should be the central focus of all discussion here.
If you look at your examples, you will find that they are all *intra-domain*
and do not address domain-switching at all -
a. "if you learned the associations A-B and B-C, then A will predict C.
> That is called "reasoning"
b) a word-word matrix M from a large text corpus, ..gives you something similar
to
> your free association chain like rain-wet-water-...
No domain-switching there.
Compare these with my
b) domain-switching chain -"COW" - DOG - TAIL - CURRENT CRISIS - LOCAL VS
>> GLOBAL
>> THINKING - WHAT A NICE DAY - MUST GET ON- CANT SPEND MUCH
>> MORE TIME ON
>> THIS...."
(switching between the domains of - Animals - Politics/Economics - Weather -
Personal Timetable)
a) your (extremely limited) idea of (logical) reasoning is also entirely
intra-domain - the domain of the Alphabet, (A-B-C).
But my creative and similar creative chains are analogous to switching from
say an Alphabet domain (A-B-C) to a Foreign Languages domain (alpha - omega)
to a Semiotics one (symbol - sign - representation) to a Fonts one (Courier -
Times Roman) etc. etc. - i.e. we could all easily and spontaneously form such
a domain-switching chain.
Your programs and all the programs ever written are still incapable of doing
this - switching domains. This, it bears repeating, is the problem of AGI.
Because you're ignoring it, you don't see that you're in effect maintaining an
absurdity - which is that the human brain cannot deliberately form new,
surprising domain connections and comparisons. Everything according to you
stems from memory recall/ previous associations (and presumably, chance, random
new connections ).
Complete nonsense.
It leads me to elaborate my claim - not only is the brain freely - it is
*infinitely domain-switching* (or "practically endlessly").
To demonstrate this, we can focus on "directed free association" .as opposed to
my undirected,chain above. Instead of just rambling, try focussing on a single
idea, and keep associating anew with it.
So I start with ANIMALS. And freely associating, I get GAZA - TAILS - DISEASE
- CARTOONS - FEET - OXYGEN - EYES - NOSE - AFGHANISTAN - DESERT - MARS . And if
you'll try it, you'll find that I and you can go on for ever, forming a great
many altogether *new* and even surprising domain connections with a single
idea. (If the brain can switch domains infinitely, it can obviously do this).
[Explanation for connecton with AFGHANISTAN ("what animals are there?) - DESERT
("not many animals there?) - MARS ("no animals there?")].
Your programs can't do this precisely because they are confined to single
domains and single databases - and even if they start searching the net, they
are still confined by single-domain *rules-of-connection/association*. But the
human brain is not. It can freely associate with "rules" and even "modes of
reasoning." or "modes of association" too - and produce infinite forms of
reasoning (by contrast with your limited conceptions here).
Note by the way that we can turn the above into "problem-directed free
association" - start say with THE PROBLEM OF GAZA - and freely associate
endless domain aspects of the problem, and endless domain types of solution -
and come up with at least technically new solutions. (Buzan's mindmaps
basically depend on this). And now we have a vital and *practical* form of
human reasoning, not just a relatively idle one - and one that is utterly
beyond the extremely narrow confines of the logic and mathematics that you can
only envisage.
So it's worth examining and trying to explain this human capacity of free
association, free/infinite domain-switching, because you have neither any way
of explaining it, nor of reproducing it.
But, if you're not prepared to step outside your normal logicomathematical ruts
- note that you couldn't even be bothered to take a few seconds to form and
analyse your own chain of association - then, I suggest you'll never make any
AGI progress.
P.S. One important reason for the brain's capacity to infinitely switch domains
is that, in the real world, "everything connects" - or at any rate all things
have an unlimited number of features and dimensions in common. But the
computers that you envisage, being connected only to logical databses with
highly limited associativity and unconnected to the real world, have no way of
seeing and otherwise sensing this - or of "having a fresh look" at things..
Matt/Mike,
>
> Your own thought processes only seem mysterious because you can't predict
> what you will think without actually thinking it. It's not just a property
> of the human brain, but of all Turing machines. No program can
> non-trivially model itself. (By model, I mean that P models Q if for any
> input x, P can compute the output Q(x). By non-trivial, I mean that P does
> something else besides just model Q. (Every program trivially models
> itself). The proof is that for P to non-trivially model Q requires K(P) >
> K(Q), where K is Kolmogorov complexity, because P needs a description of Q
> plus whatever else it does to make it non-trivial. It is obviously not
> possible for K(P) > K(P)).
>
> So if you learned the associations A-B and B-C, then A will predict C.
> That is called "reasoning".
>
> Also, each concept is associated with thousands of other concepts, not
> just A-B. If you pick the strongest associated concept not previously
> activated, you get the semi-random thought chain you describe. You can
> demonstrate this with a word-word matrix M from a large text corpus, where
> M[i,j] is the degree to which the i'th word in the vocabulary is
> associated with the j'th word, as measured by the probability of finding
> both words near each other in the corpus. Thus, M[rain,wet] and
> M[wet,water] have high values because the words often appear in the same
> paragraph. Traversing related words in M gives you something similar to
> your free association chain like rain-wet-water-...
>
> -- Matt Mahoney, [email protected]
>
>
> --- On Thu, 1/8/09, Mike Tintner <[email protected]> wrote:
>
>> From: Mike Tintner <[email protected]>
>> Subject: Re: [agi] The Smushaby of Flatway.
>> To: [email protected]
>> Date: Thursday, January 8, 2009, 3:54 PM
>> Matt:Free association is the basic way of recalling
>> memories. If you experience A followed by B, then the next
>> time you experience A you will think of (or predict) B.
>> Pavlov demonstrated this type of learning in animals in
>> 1927.
>>
>> Matt,
>>
>> You're not thinking your argument through. Look
>> carefully at my spontaneous
>>
>> "COW" - DOG - TAIL - CURRENT CRISIS - LOCAL VS
>> GLOBAL
>> THINKING - WHAT A NICE DAY - MUST GET ON- CANT SPEND MUCH
>> MORE TIME ON
>> THIS...." etc. etc"
>>
>> that's not A-B association.
>>
>> That's 1. A-B-C then 2. Gamma-Delta then 3.
>> Languages then 4. Number of Lines in Letters.
>>
>> IOW the brain is typically not only freely associating
>> *ideas* but switching freely across, and connecting,
>> radically different *domains* in any given chain of
>> association. [e.g above from Animals to Economics/Politics
>> to Weather to Personal Timetable]
>>
>> It can do this partly because
>>
>> a) single ideas have multiple, often massively mutiple,
>> idea/domain connections in the human brain, and allow one to
>> go off in any of multiple tangents/directions
>> b) humans have many things - and therefore multiple domains
>> - on their mind at the same time concurrently - and can
>> switch as above from the immediate subject to some other
>> pressing subject domain (e.g. from economics/politics
>> (local vs global) to the weather (what a nice day).
>>
>> If your "A-B, everything-is-memory-recall" thesis
>> were true, our chains-of-thought-association would be
>> largely repetitive, and the domain switches inevitable..
>>
>> In fact, our chains (or networks) of free association and
>> domain-switching are highly creative, and each one is
>> typically, from a purely technical POV, novel and
>> surprising. (I have never connected TAIL and CURRENT CRISIS
>> before - though Animals and Politics yes. Nor have I
>> connected LOCAL VS GLOBAL THINKING before with WHAT A NICE
>> DAY and the weather).
>>
>> IOW I'm suggesting, the natural mode of human thought -
>> and our continuous streams of association - are creative.
>> And achieving such creativity is the principal problem/goal
>> of AGI.
>>
>> So maybe it's worth taking 20 secs. of time - producing
>> your own chain-of-free-association starting say with
>> "MAHONEY" and going on for another 10 or so items
>> - and trying to figure out how the result could.possibly be
>> the narrow kind of memory-recall you're arguing for.
>> It's an awful lot to ask for, but could you possibly try
>> it, analyse it and report back?
>>
>> [Ben claims to have heard every type of argument I make
>> before, (somewhat like your A-B memory claim), so perhaps
>> he can tell me where he's read before about the Freely
>> Associative, Freely Domain Switching nature of human thought
>> - I'd be interested to follow up on it].
>
-------------------------------------------
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/
Modify Your Subscription:
https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b
Powered by Listbox: http://www.listbox.com
