Re: [agi] How do we hear music
On Fri, 2010-07-23 at 23:38 +0100, Mike Tintner wrote: Michael:but those things do have patterns.. A mushroom (A) is like a cloud mushroom (B). if ( (input_source_A == An_image) AND ( input_source_B == An_image )) One pattern is that they both came from an image source, and I just used maths + logic to prove it Michael, This is a bit desperate isn't it? It's a common misconception that high level queries aren't very good. Imagine 5 senses, sight, touch taste .. etc. We confirm the input is from sight. By doing this we potentially reduce the combination of what it could be by 4/5 ~ 80%. which is pretty awesome. Computer programs know nothing. You have to tell them everything (narrow AI) or allow the mechanics to find out things for themselves. They both come from image sources. So do a zillion other images, from Obama to dung - so they're all alike? Everything in the world is alike and metaphorical for everything else? And their images must be alike because they both have an 'o' and a 'u' in their words, (not their images)- unless you're a Chinese speaker. Pace Lear, that way madness lies. Why don't you apply your animation side to the problem - and analyse the images per images, and how to compare them as images? Some people in AGI although not AFAIK on this forum are actually addressing the problem. I'm sure *you* can too. -- From: Michael Swan ms...@voyagergaming.com Sent: Friday, July 23, 2010 8:28 AM To: agi agi@v2.listbox.com Subject: Re: [agi] How do we hear music On Fri, 2010-07-23 at 03:45 +0100, Mike Tintner wrote: Let's crystallise the problem - all the unsolved problems of AGI - visual object recognition, conceptualisation, analogy, metaphor, creativity, language understanding and generation - are problems where you're dealing with freeform, irregular patchwork objects - objects which clearly do not fit any *patterns* - the raison d'etre of maths . To focus that , these objects do not have common parts in more or less precisely repeating structures - i.e. fit patterns. A cartoon and a photo of the same face may have no parts or structure in common. Ditto different versions of the Google logo. Zero common parts or structure Ditto cloud and mushroom - no common parts, or common structure. Yet the mind amazingly can see likenesses between all these things. Just about all the natural objects in the world , with some obvious exceptions, do not fit common patterns - they do not have the same parts in precisely the same places/structures. They may have common loose organizations of parts - e.g. mouths, eyes, noses, lips - but they are not precisely patterned. So you must explain how a mathematical approach, wh. is all about recognizing patterns, can apply to objects wh. do not fit patterns. You won't be able to - because if you could bring yourselves to look at the real world or any depictions of it other than geometric, (metacognitively speaking),you would see for yourself that these objects don't have precise patterns. It's obvious also that when the mind likens a cloud to a mushroom, it cannot be using any math. techniques. .. but those things do have patterns.. A mushroom (A) is like a cloud mushroom (B). if ( (input_source_A == An_image) AND ( input_source_B == An_image )) One pattern is that they both came from an image source, and I just used maths + logic to prove it. But we have to understand how the mind does do that - because it's fairly clearly the same technique the mind also uses to conceptualise even more vastly different forms such as those of chair, tree, dog, cat. And that technique - like concepts themselves - is at the heart of AGI. And you can sit down and analyse the problem visually, physically and see also pretty obviously that if the mind can liken such physically different objects as cloud and mushroom, then it HAS to do that with something like a fluid schema. There's broadly no other way but to fluidly squash the objects to match each other (there could certainly be different techniques of achieving that - but the broad principles are fairly self evident). Cloud and mushroom certainly don't match formulaically, mathematically. Neither do those different versions of a tune. Or the different faces of Madonna. But what we've got here is people who don't in the final analysis give a damn about how to solve AGI - if it's a choice between doing maths and failing, and having some kind of artistic solution to AGI that actually works, most people here will happily fail forever. Mathematical AI has indeed consistently failed at AGI. You have to realise, mathematicians have a certain kind of madness. Artists don't go around saying God is an artist, or everything is art. Only
Re: [agi] How do we hear music
On Fri, 2010-07-23 at 03:45 +0100, Mike Tintner wrote: Let's crystallise the problem - all the unsolved problems of AGI - visual object recognition, conceptualisation, analogy, metaphor, creativity, language understanding and generation - are problems where you're dealing with freeform, irregular patchwork objects - objects which clearly do not fit any *patterns* - the raison d'etre of maths . To focus that , these objects do not have common parts in more or less precisely repeating structures - i.e. fit patterns. A cartoon and a photo of the same face may have no parts or structure in common. Ditto different versions of the Google logo. Zero common parts or structure Ditto cloud and mushroom - no common parts, or common structure. Yet the mind amazingly can see likenesses between all these things. Just about all the natural objects in the world , with some obvious exceptions, do not fit common patterns - they do not have the same parts in precisely the same places/structures. They may have common loose organizations of parts - e.g. mouths, eyes, noses, lips - but they are not precisely patterned. So you must explain how a mathematical approach, wh. is all about recognizing patterns, can apply to objects wh. do not fit patterns. You won't be able to - because if you could bring yourselves to look at the real world or any depictions of it other than geometric, (metacognitively speaking),you would see for yourself that these objects don't have precise patterns. It's obvious also that when the mind likens a cloud to a mushroom, it cannot be using any math. techniques. .. but those things do have patterns.. A mushroom (A) is like a cloud mushroom (B). if ( (input_source_A == An_image) AND ( input_source_B == An_image )) One pattern is that they both came from an image source, and I just used maths + logic to prove it. But we have to understand how the mind does do that - because it's fairly clearly the same technique the mind also uses to conceptualise even more vastly different forms such as those of chair, tree, dog, cat. And that technique - like concepts themselves - is at the heart of AGI. And you can sit down and analyse the problem visually, physically and see also pretty obviously that if the mind can liken such physically different objects as cloud and mushroom, then it HAS to do that with something like a fluid schema. There's broadly no other way but to fluidly squash the objects to match each other (there could certainly be different techniques of achieving that - but the broad principles are fairly self evident). Cloud and mushroom certainly don't match formulaically, mathematically. Neither do those different versions of a tune. Or the different faces of Madonna. But what we've got here is people who don't in the final analysis give a damn about how to solve AGI - if it's a choice between doing maths and failing, and having some kind of artistic solution to AGI that actually works, most people here will happily fail forever. Mathematical AI has indeed consistently failed at AGI. You have to realise, mathematicians have a certain kind of madness. Artists don't go around saying God is an artist, or everything is art. Only mathematicians have that compulsion to reduce everything to maths, when the overwhelming majority of representations are clearly not mathematical - or claim that the obviously irregular abstract arts (think Pollock) are mathematical. You're in good company - Wolfram, a brilliant fellow, thinks his patterns constitute a new kind of science, when the vast majority of scientists can see they only constitute a new kind of pattern, and do not apply to the real world. Look again - the brain is primarily a patchwork adapted to a patchwork, very extensively unpatterned world - incl. the internet itself - adapted primarily not to neat, patterned networks, but to tangled, patchwork, non-mathematical webs. See fotos. The outrageous one here is not me. -- From: Michael Swan ms...@voyagergaming.com Sent: Friday, July 23, 2010 2:19 AM To: agi agi@v2.listbox.com Subject: Re: [agi] How do we hear music Hi, Sometimes outrageous comments are a catalyst for better ideas. On Fri, 2010-07-23 at 01:48 +0200, Jan Klauck wrote: Mike Tintner trolled And maths will handle the examples given : same tunes - different scales, different instruments same face - cartoon, photo same logo - different parts [buildings/ fruits/ human figures] Unfortunately I forgot. The answer is somewhere down there: http://en.wikipedia.org/wiki/Eigenvalue,_eigenvector_and_eigenspace http://en.wikipedia.org/wiki/Pattern_recognition http://en.wikipedia.org/wiki/Curve_fitting http://en.wikipedia.org/wiki/System_identification No-one has successfully integrated these concepts
Re: [agi] How do we hear music
Hi, Sometimes outrageous comments are a catalyst for better ideas. On Fri, 2010-07-23 at 01:48 +0200, Jan Klauck wrote: Mike Tintner trolled And maths will handle the examples given : same tunes - different scales, different instruments same face - cartoon, photo same logo - different parts [buildings/ fruits/ human figures] Unfortunately I forgot. The answer is somewhere down there: http://en.wikipedia.org/wiki/Eigenvalue,_eigenvector_and_eigenspace http://en.wikipedia.org/wiki/Pattern_recognition http://en.wikipedia.org/wiki/Curve_fitting http://en.wikipedia.org/wiki/System_identification No-one has successfully integrated these concepts into a working AGI, despite numerous attempts. Even though these concept feel general, when implemented, only narrow or affected by combinatorial explosion have succeeded. revealing them to be the same - how exactly? Why should anybody explain that mystery to you? You are not an accepted member of the Grand Lodge of AGI Masons or its affiliates. Or you could take two arseholes - same kind of object, but radically different configurations - maths will show them to belong to the same category, how? How will you do it? By licking them? Personal attacks only weaken your arguments. --- 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/?; Powered by Listbox: http://www.listbox.com --- 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=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] The Collective Brain
On Wed, 2010-07-21 at 02:25 +0100, Mike Tintner wrote: By implicitly pretending that artificial brains exist - in the form of computer programs - you (and most AGI-ers), deflect attention away from all the unsolved dimensions of what is required for an independent brain-cum-living system, I for one would like to see this brain-cum living system. It's erotic intelligence would be astronomical! natural or artificial. One of those dimensions is a society of brains/systems. Another is a body. And there are more., none of wh. are incorporated in computer programs - they only represent one dimension of what is needed for a brain. -- From: Jan Klauck jkla...@uni-osnabrueck.de Sent: Wednesday, July 21, 2010 1:56 AM To: agi agi@v2.listbox.com Subject: Re: [agi] The Collective Brain Mike Tintner wrote No, the collective brain is actually a somewhat distinctive idea. Just a way of looking at social support networks. Even social philosophers centuries ago had similar ideas--they were lacking our technical understanding and used analogies from biology (organicism) instead. more like interdependently functioning with society As I said it's long known to economists and sociologists. There's even an African proverb pointing at this: It takes a village to raise a child. System researcher investigate those interdependencies since decades. Did you watch the talk? No flash here. I just answer on what you're writing. The evidence of the idea's newness is precisely the discussions of superAGI's and AGI futures by the groups here We talked about the social dimensions some times. It's not the most important topic around here, but that doesn't mean we're all ignorant. In case you haven't noticed I'm not building an AGI, I'm interested in the stuff around, e.g., tests, implementation strategies etc. by the means of social simulation. Your last question is also an example of cocooned-AGI thinking? Which brains? The only real AGI brains are those of living systems A for Artificial. Living systems don't qualify for A. My question was about certain attributes of brains (whether natural or artificial). Societies are constrained by their members' capacities. A higher individual capacity can lead to different dependencies and new ways groups and societies are working. --- 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/?; Powered by Listbox: http://www.listbox.com --- 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/?; Powered by Listbox: http://www.listbox.com --- 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=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] The Collective Brain
The most powerful concept in the universe is working together. If atoms didn't attract and repel each other, then we'd have a universe where nothing ever happened. So, Collective Brain is a subset of the collective intelligence of the universe. On Wed, 2010-07-21 at 02:25 +0100, Mike Tintner wrote: You partly illustrate my point - you talk of artificial brains as if they actually exist - there aren't any; there are only glorified, extremely complex calculators/computer programs - extensions/augmentations of individual faculties of human brains. To obviously exaggerate, it's somewhat as if you were to talk of cameras as brains. By implicitly pretending that artificial brains exist - in the form of computer programs - you (and most AGI-ers), deflect attention away from all the unsolved dimensions of what is required for an independent brain-cum-living system, natural or artificial. One of those dimensions is a society of brains/systems. Another is a body. And there are more., none of wh. are incorporated in computer programs - they only represent one dimension of what is needed for a brain. Yes you may know these things some times as you say, but most of the time they're forgotten. -- From: Jan Klauck jkla...@uni-osnabrueck.de Sent: Wednesday, July 21, 2010 1:56 AM To: agi agi@v2.listbox.com Subject: Re: [agi] The Collective Brain Mike Tintner wrote No, the collective brain is actually a somewhat distinctive idea. Just a way of looking at social support networks. Even social philosophers centuries ago had similar ideas--they were lacking our technical understanding and used analogies from biology (organicism) instead. more like interdependently functioning with society As I said it's long known to economists and sociologists. There's even an African proverb pointing at this: It takes a village to raise a child. System researcher investigate those interdependencies since decades. Did you watch the talk? No flash here. I just answer on what you're writing. The evidence of the idea's newness is precisely the discussions of superAGI's and AGI futures by the groups here We talked about the social dimensions some times. It's not the most important topic around here, but that doesn't mean we're all ignorant. In case you haven't noticed I'm not building an AGI, I'm interested in the stuff around, e.g., tests, implementation strategies etc. by the means of social simulation. Your last question is also an example of cocooned-AGI thinking? Which brains? The only real AGI brains are those of living systems A for Artificial. Living systems don't qualify for A. My question was about certain attributes of brains (whether natural or artificial). Societies are constrained by their members' capacities. A higher individual capacity can lead to different dependencies and new ways groups and societies are working. --- 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/?; Powered by Listbox: http://www.listbox.com --- 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/?; Powered by Listbox: http://www.listbox.com --- 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=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Is there any Contest or test to ensure that a System is AGI?
Numbers combined together are a form of language that can form every other language. and... If you insist on using a natural language, why don't you use the language most natural to computers - ie code ( which can directly translates to numbers - machine language ...) Code is better because you can automatically test then observe to see if your new code combination works. It's also more pedantic and doesn't allow ambiguity. On Sun, 2010-07-18 at 21:28 +0100, Ian Parker wrote: In my view the main obstacle to AGI is the understanding of Natural Language. If we have NL comprehension we have the basis for doing a whole host of marvellous things. There is the Turing test. A good question to ask is What is the difference between laying concrete at 50C and fighting Israel. Google translated wsT jw AlmErkp or وسط جو المعركة as central air battle. Correct is the climatic environmental battle or a more free translation would be the battle against climate and environment. In Turing competitions no one ever asks the questions that really would tell AGI apart from a brand X chatterbox. http://sites.google.com/site/aitranslationproject/Home/formalmethods We can I think say that anything which can carry out the program of my blog would be well on its way. AGI will also be the link between NL and formal mathematics. Let me take yet another example. http://sites.google.com/site/aitranslationproject/deepknowled Google translated it as 4 times the temperature. Ponder this, you have in fact 3 chances to get this right. 1) درجة means degree. GT has not translated this word. In this context it means power. 2) If you search for Stefan Boltzmann or Black Body Google gives you the correct law. 3) The translation is obviously mathematically incorrect from the dimensional stand-point. This 3 things in fact represent different aspects of knowledge. In AGI they all have to be present. The other interesting point is that there are programs in existence now that will address the last two questions. A translator that produces OWL solves 2. If we match up AGI to Mizar we can put dimensions into the proof engine. There are a great many things on the Web which will solve specific problems. NL is THE problem since it will allow navigation between the different programs on the Web. MOLTO BTW does have its mathematical parts even though it is primerally billed as a translator. - Ian Parker On 18 July 2010 14:41, deepakjnath deepakjn...@gmail.com wrote: Yes, but is there a competition like the XPrize or something that we can work towards. ? On Sun, Jul 18, 2010 at 6:40 PM, Panu Horsmalahti nawi...@gmail.com wrote: 2010/7/18 deepakjnath deepakjn...@gmail.com I wanted to know if there is any bench mark test that can really convince majority of today's AGIers that a System is true AGI? Is there some real prize like the XPrize for AGI or AI in general? thanks, Deepak Have you heard about the Turing test? - Panu Horsmalahti agi | Archives | Modify Your Subscription -- cheers, Deepak agi | Archives | Modify Your Subscription agi | Archives | Modify Your Subscription --- 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=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] What is the smallest set of operations that can potentially define everything and how do you combine them ?
On Wed, 2010-07-14 at 07:48 -0700, Matt Mahoney wrote:
Actually, Fibonacci numbers can be computed without loops or recursion.
int fib(int x) {
return round(pow((1+sqrt(5))/2, x)/sqrt(5));
}
;) I know. I was wondering if someone would pick up on it. This won't
prove that brains have loops though, so I wasn't concerned about the
shortcuts.
unless you argue that loops are needed to compute sqrt() and pow().
I would find it extremely unlikely that brains have *, /, and even more
unlikely to have sqrt and pow inbuilt. Even more unlikely, even if it
did have them, to figure out how to combine them to round(pow((1
+sqrt(5))/2, x)/sqrt(5)).
Does this mean we should discount all maths that use any complex
operations ?
I suspect the brain is full of look-up tables mainly, with some fairly
primitive methods of combining the data.
eg What's 6 / 3 ?
ans = 2 most people would get that because it's been wrote learnt, a
common problem.
What 3456/6 ?
we don't know, at least not from the top of our head.
The brain and DNA use redundancy and parallelism and don't use loops because
their operations are slow and unreliable. This is not necessarily the best
strategy for computers because computers are fast and reliable but don't have
a
lot of parallelism.
The brains slow and unreliable methods I think are the price paid for
generality and innately unreliable hardware. Imagine writing a computer
program that runs for 120 years without crashing and surviving damage
like a brain can. I suspect the perfect AGI program is a rigorous
combination of the 2.
-- Matt Mahoney, matmaho...@yahoo.com
- Original Message
From: Michael Swan ms...@voyagergaming.com
To: agi agi@v2.listbox.com
Sent: Wed, July 14, 2010 12:18:40 AM
Subject: Re: [agi] What is the smallest set of operations that can
potentially
define everything and how do you combine them ?
Brain loops:
Premise:
Biological brain code does not contain looping constructs, or the
ability to creating looping code, (due to the fact they are extremely
dangerous on unreliable hardware) except for 1 global loop that fires
about 200 times a second.
Hypothesis:
Brains cannot calculate iterative problems quickly, where calculations
in the previous iteration are needed for the next iteration and, where
brute force operations are the only valid option.
Proof:
Take as an example, Fibonacci numbers
http://en.wikipedia.org/wiki/Fibonacci_number
What are the first 100 Fibonacci numbers?
int Fibonacci[102];
Fibonacci[0] = 0;
Fibonacci[1] = 1;
for(int i = 0; i 100; i++)
{
// Getting the next Fibonacci number relies on the previous values
Fibonacci[i+2] = Fibonacci[i] + Fibonacci[i+1];
}
My brain knows the process to solve this problem but it can't directly
write a looping construct into itself. And so it solves it very slowly
compared to a computer.
The brain probably consists of vast repeating look-up tables. Of course,
run in parallel these seem fast.
DNA has vast tracks of repeating data. Why would DNA contain repeating
data, instead of just having the data once and the number of times it's
repeated like in a loop? One explanation is that DNA can't do looping
construct either.
On Wed, 2010-07-14 at 02:43 +0100, Mike Tintner wrote:
Michael: We can't do operations that
require 1,000,000 loop iterations. I wish someone would give me a PHD
for discovering this ;) It far better describes our differences than any
other theory.
Michael,
This isn't a competitive point - but I think I've made that point several
times (and so of course has Hawkins). Quite obviously, (unless you think
the
brain has fabulous hidden powers), it conducts searches and other
operations
with extremely few limited steps, and nothing remotely like the routine
millions to billions of current computers. It must therefore work v.
fundamentally differently.
Are you saying anything significantly different to that?
--
From: Michael Swan ms...@voyagergaming.com
Sent: Wednesday, July 14, 2010 1:34 AM
To: agi agi@v2.listbox.com
Subject: Re: [agi] What is the smallest set of operations that can
potentially define everything and how do you combine them ?
On Tue, 2010-07-13 at 07:00 -0400, Ben Goertzel wrote:
Well, if you want a simple but complete operator set, you can go with
-- Schonfinkel combinator plus two parentheses
I'll check this out soon.
or
-- S and K combinator plus two parentheses
and I suppose you could add
-- input
-- output
-- forget
statements to this, but I'm not sure what this gets you...
Actually, adding other operators doesn't necessarily
increase the search space your AI faces -- rather, it
**decreases** the search space **if** you choose the right operators,
that
encapsulate regularities
Re: [agi] What is the smallest set of operations that can potentially define everything and how do you combine them ?
On Wed, 2010-07-14 at 17:51 -0700, Matt Mahoney wrote:
Michael Swan wrote:
What 3456/6 ?
we don't know, at least not from the top of our head.
No, it took me about 10 or 20 seconds to get 576. Starting with the first
digit,
3/6 = 1/2 (from long term memory) and 3 is in the thousands place, so 1/2 of
1000 is 500 (1/2 = .5 from LTM). I write 500 into short term memory (STM),
which
only has enough space to hold about 7 digits. Then to divide 45/6 I get 42/6
= 7
with a remainder of 3, or 7.5, but since this is in the tens place I get 75.
I
put 75 in STM, add to 500 to get 575, put the result back in STM replacing
500
and 75 for which there is no longer room. Finally, 6/6 = 1, which I add to
575
to get 576. I hold this number in STM long enough to check with a calculator.
The brain does have one global loop, which I think goes at about 100~200
hertz. I would argue that your using that. Also note, brain are unlikely
to use RAM. Memory is most likely stored very locally to the process, as
the brain prob. can't access memory frivolously like in a computer. So,
the processes that require going backwards have to wait for the next
global loop to get the data, causing massive loss in time.
So about (~10sec * ~100hertz)= 1000+ loops I suspect is about right.
One could argue that this calculation in my head uses a loop iterator (in
STM)
to keep track of which digit I am working on. It definitely involves a
sequence
of instructions with intermediate results being stored temporarily. The brain
can only execute 2 or 3 sequential instructions per second and has very
limited
short term memory, so it needs to draw from a large database of rules to
perform
calculations like this. A calculator, being faster and having more RAM, is
able
to use simpler but more tedious algorithms such as converting to binary,
division by shift and subtract, and converting back to decimal. Doing this
with
a carbon based computer would require pencil and paper to make up for lack of
STM, and it would require enough steps to have a high probability of making a
mistake.
Intelligence = knowledge + computing power.
+ an clever way of using that computing power
The human brain has a lot of
knowledge. The calculator has less knowledge, but makes up for it in speed
and
memory.
-- Matt Mahoney, matmaho...@yahoo.com
- Original Message
From: Michael Swan ms...@voyagergaming.com
To: agi agi@v2.listbox.com
Sent: Wed, July 14, 2010 7:53:33 PM
Subject: Re: [agi] What is the smallest set of operations that can
potentially
define everything and how do you combine them ?
On Wed, 2010-07-14 at 07:48 -0700, Matt Mahoney wrote:
Actually, Fibonacci numbers can be computed without loops or recursion.
int fib(int x) {
return round(pow((1+sqrt(5))/2, x)/sqrt(5));
}
;) I know. I was wondering if someone would pick up on it. This won't
prove that brains have loops though, so I wasn't concerned about the
shortcuts.
unless you argue that loops are needed to compute sqrt() and pow().
I would find it extremely unlikely that brains have *, /, and even more
unlikely to have sqrt and pow inbuilt. Even more unlikely, even if it
did have them, to figure out how to combine them to round(pow((1
+sqrt(5))/2, x)/sqrt(5)).
Does this mean we should discount all maths that use any complex
operations ?
I suspect the brain is full of look-up tables mainly, with some fairly
primitive methods of combining the data.
eg What's 6 / 3 ?
ans = 2 most people would get that because it's been wrote learnt, a
common problem.
What 3456/6 ?
we don't know, at least not from the top of our head.
The brain and DNA use redundancy and parallelism and don't use loops
because
their operations are slow and unreliable. This is not necessarily the best
strategy for computers because computers are fast and reliable but don't
have a
lot of parallelism.
The brains slow and unreliable methods I think are the price paid for
generality and innately unreliable hardware. Imagine writing a computer
program that runs for 120 years without crashing and surviving damage
like a brain can. I suspect the perfect AGI program is a rigorous
combination of the 2.
-- Matt Mahoney, matmaho...@yahoo.com
- Original Message
From: Michael Swan ms...@voyagergaming.com
To: agi agi@v2.listbox.com
Sent: Wed, July 14, 2010 12:18:40 AM
Subject: Re: [agi] What is the smallest set of operations that can
potentially
define everything and how do you combine them ?
Brain loops:
Premise:
Biological brain code does not contain looping constructs, or the
ability to creating looping code, (due to the fact they are extremely
dangerous on unreliable hardware) except for 1 global loop that fires
about 200 times a second.
Hypothesis:
Brains cannot calculate iterative problems quickly, where
Re: [agi] What is the smallest set of operations that can potentially define everything and how do you combine them ?
On Thu, 2010-07-15 at 01:37 +0100, Mike Tintner wrote: Michael :The brains slow and unreliable methods I think are the price paid for generality and innately unreliable hardware Yes to one - nice to see an AGI-er finally starting to join up the dots, instead of simply dismissing the brain's massive difficulties in maintaining a train of thought. No to two -innately unreliable hardware is the price of innately *adaptable* hardware - that can radically grow and rewire (wh. is the other advantage the brain has over computers). Any thoughts about that and what in more detail are the advantages of an organic computer? Program software can rewire themselves in some senses, one creates virtual hardware inside the program as though it was real hardware. But it's extremely rare to find ones that are purely general, so much so I doubt purely general ones even exist. Are NN's purely general? Are GA's purely general? I thought perhaps code that writes code could potentially reach such a lofty goal (as it can turn into a GA or NN or , well, anything). Then I thought the code writing the code restricts what the written code can be. So, then I made some simple experiments of the code modifying itself. The end result was surprisingly ( at least I suspect it was) similar to DNA. I still had a large section of code, whose purpose was to read part itself, and modify it, and this large piece of code had no bearing in what the modified code actually did. DNA has 2 sections, a coding section, which actually most of the hard work, and poorly named junk DNA (or non-coding DNA), which most biologist thought did nothing, until they discovered it doing stuff all over the place but in a somewhat discrete, subtle fashion. So, is my experiment 6 http://codegenerationdesign.webs.com/index.htm the first ever program to roughly mimic the programming of DNA ? I find this really hard to prove, but I think it remains a possibility. Apparently, Biologists don't think much my degree in biology from the University of Wikipedia, nature docs, and other random stuff you read from the internet. In addition, the unreliable hardware is also a price of global ardware - that has the basic capacity to connect more or less any bit of information in any part of the brain with any bit of information in any other part of the brain - as distinct from the local hardware of computers wh. have to go through limited local channels to limited local stores of information to make v. limited local kinds of connections. Well, that's my tech-ignorant take on it - but perhaps you can expand on the idea. I would imagine v. broadly the brain is globally connected vs the computer wh. is locally connected. Yep, the ability to grab memory from anywhere is called RAM - Random Access Memory. A single neurons can only access data from it's 25,000 connections, which sounds like a lot, but isn't because computers can access a theoretical infinite set of data. Being that the program in a brain can only go forward, how does it tell other neurons that it wants data about X that is behind it ? One theory, is that certain neurons detect that they need more data, and create a greater positive charge to attract more of negatively charged data. So in a sense they sux more data into themselves, effectively sending a different, non-dangerous backward running signal. (Author note: that I can't prove this at all, and is just a possibility) --- 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/?; Powered by Listbox: http://www.listbox.com --- 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=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] What is the smallest set of operations that can potentially define everything and how do you combine them ?
I'd argue that mathematical operations are unnecesary, we don't even have integer support inbuilt. I'd disagree. is a mathematical operation, and in combination can become an enormous number of concepts. Sure, I think the brain is more sensibly understood in a programattical sense than mathematical. I say programattical because it probably has 100 billion or so conditional statements, a difficult thing to represent mathematically. Even so, each conditional is going to have maths constructs in it. The number meme is a bit of a hack on top of language that has been modified throughout the years. We have a peripheral that allows us decent support for the numbers 1-10, but beyond that numbers are basically words to which several different finicky grammars can be applied as far as our brains are concerned. True, but numbers awesomeness lies it there power to represent relative differences between any concepts. With this power, numbers are a universal language, a language that can represent any other language, and hence, the ideal language and probably only real choice for an AGI. agi | Archives | Modify Your Subscription --- 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=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] What is the smallest set of operations that can potentially define everything and how do you combine them ?
On Tue, 2010-07-13 at 07:00 -0400, Ben Goertzel wrote:
Well, if you want a simple but complete operator set, you can go with
-- Schonfinkel combinator plus two parentheses
I'll check this out soon.
or
-- S and K combinator plus two parentheses
and I suppose you could add
-- input
-- output
-- forget
statements to this, but I'm not sure what this gets you...
Actually, adding other operators doesn't necessarily
increase the search space your AI faces -- rather, it
**decreases** the search space **if** you choose the right operators, that
encapsulate regularities in the environment faced by the AI
Unfortunately, an AGI needs to be absolutely general. You are right that
higher level concepts reduce combinations, however, using them, will
increase combinations for simpler operator combinations, and if you
miss a necessary operator, then some concepts will be impossible to
achieve. The smallest set can define higher level concepts, these
concepts can be later integrated as single operations, which means
using operators than can be understood in terms of smaller operators
in the beginning, will definitely increase you combinations later on.
The smallest operator set is like absolute zero. It has a defined end. A
defined way of finding out what they are.
Exemplifying this, writing programs doing humanly simple things
using S and K is a pain and involves piling a lot of S and K and parentheses
on top of each other, whereas if we introduce loops and conditionals and
such, these programs get shorter. Because loops and conditionals happen
to match the stuff that our human-written programs need to do...
Loops are evil in most situations.
Let me show you why:
Draw a square using put_pixel(x,y)
// loops are more scalable, but, damage this code anywhere and it can
potentially kill every other process, not just itself. This is why
computers die all the time.
for (int x = 0; x 2; x++)
{
for (int y = 0; y 2; y++)
{
put_pixel(x,y);
}
}
opposed to
/* The below is faster (even on single step instructions), and can be
run in parallel, damage resistant ( ie destroy put_pixel(0,1); and the
rest of the code will still run), is less scalable ( more code is
required for larger operations)
put_pixel(0,0);
put_pixel(0,1);
put_pixel(1,0);
put_pixel(1,1);
The lack of loops in the brain is a fundamental difference between
computers and brains. Think about it. We can't do operations that
require 1,000,000 loop iterations. I wish someone would give me a PHD
for discovering this ;) It far better describes our differences than any
other theory.
A better question IMO is what set of operators and structures has the
property that the compact expressions tend to be the ones that are useful
for survival and problem-solving in the environments that humans and human-
like AIs need to cope with...
For me that is stage 2.
-- Ben G
On Tue, Jul 13, 2010 at 1:43 AM, Michael Swan ms...@voyagergaming.com wrote:
Hi,
I'm interested in combining the simplest, most derivable operations
( eg operations that cannot be defined by other operations) for creating
seed AGI's. The simplest operations combined in a multitude ways can
form extremely complex patterns, but the underlying logic may be
simple.
I wonder if varying combinations of the smallest set of operations:
{ , memory (= for memory assignment), ==, (a logical way to
combine them), (input, output), () brackets }
can potentially learn and define everything.
Assume all input is from numbers.
We want the smallest set of elements, because less elements mean less
combinations which mean less chance of hitting combinatorial explosion.
helps for generalisation, reducing combinations.
memory(=) is for hash look ups, what should one remember? What can be
discarded?
== This does a comparison between 2 values x == y is 1 if x and y are
exactly the same. Returns 0 if they are not the same.
(a logical way to combine them) Any non-narrow algorithm that reduces
the raw data into a simpler state will do. Philosophically like
Solomonoff Induction. This is the hardest part. What is the most optimal
way of combining the above set of operations?
() brackets are used to order operations.
Conditionals (only if statements) + memory assignment are the only valid
form of logic - ie no loops. Just repeat code if you want loops.
If you think that the set above cannot define everything, then what is
the smallest set of operations that can potentially define everything?
--
Some proofs / Thought experiments :
1) Can , ==, (), and memory define other logical operations like
(AND gate) ?
I propose that x==y==1 defines xy
xy x==y==1
00 = 0 0==0==1 = 0
10 = 0 1==0==1 = 0
01 = 0 0==1==1 = 0
11 = 1 1==1==1
Re: [agi] What is the smallest set of operations that can potentially define everything and how do you combine them ?
Brain loops:
Premise:
Biological brain code does not contain looping constructs, or the
ability to creating looping code, (due to the fact they are extremely
dangerous on unreliable hardware) except for 1 global loop that fires
about 200 times a second.
Hypothesis:
Brains cannot calculate iterative problems quickly, where calculations
in the previous iteration are needed for the next iteration and, where
brute force operations are the only valid option.
Proof:
Take as an example, Fibonacci numbers
http://en.wikipedia.org/wiki/Fibonacci_number
What are the first 100 Fibonacci numbers?
int Fibonacci[102];
Fibonacci[0] = 0;
Fibonacci[1] = 1;
for(int i = 0; i 100; i++)
{
// Getting the next Fibonacci number relies on the previous values
Fibonacci[i+2] = Fibonacci[i] + Fibonacci[i+1];
}
My brain knows the process to solve this problem but it can't directly
write a looping construct into itself. And so it solves it very slowly
compared to a computer.
The brain probably consists of vast repeating look-up tables. Of course,
run in parallel these seem fast.
DNA has vast tracks of repeating data. Why would DNA contain repeating
data, instead of just having the data once and the number of times it's
repeated like in a loop? One explanation is that DNA can't do looping
construct either.
On Wed, 2010-07-14 at 02:43 +0100, Mike Tintner wrote:
Michael: We can't do operations that
require 1,000,000 loop iterations. I wish someone would give me a PHD
for discovering this ;) It far better describes our differences than any
other theory.
Michael,
This isn't a competitive point - but I think I've made that point several
times (and so of course has Hawkins). Quite obviously, (unless you think the
brain has fabulous hidden powers), it conducts searches and other operations
with extremely few limited steps, and nothing remotely like the routine
millions to billions of current computers. It must therefore work v.
fundamentally differently.
Are you saying anything significantly different to that?
--
From: Michael Swan ms...@voyagergaming.com
Sent: Wednesday, July 14, 2010 1:34 AM
To: agi agi@v2.listbox.com
Subject: Re: [agi] What is the smallest set of operations that can
potentially define everything and how do you combine them ?
On Tue, 2010-07-13 at 07:00 -0400, Ben Goertzel wrote:
Well, if you want a simple but complete operator set, you can go with
-- Schonfinkel combinator plus two parentheses
I'll check this out soon.
or
-- S and K combinator plus two parentheses
and I suppose you could add
-- input
-- output
-- forget
statements to this, but I'm not sure what this gets you...
Actually, adding other operators doesn't necessarily
increase the search space your AI faces -- rather, it
**decreases** the search space **if** you choose the right operators,
that
encapsulate regularities in the environment faced by the AI
Unfortunately, an AGI needs to be absolutely general. You are right that
higher level concepts reduce combinations, however, using them, will
increase combinations for simpler operator combinations, and if you
miss a necessary operator, then some concepts will be impossible to
achieve. The smallest set can define higher level concepts, these
concepts can be later integrated as single operations, which means
using operators than can be understood in terms of smaller operators
in the beginning, will definitely increase you combinations later on.
The smallest operator set is like absolute zero. It has a defined end. A
defined way of finding out what they are.
Exemplifying this, writing programs doing humanly simple things
using S and K is a pain and involves piling a lot of S and K and
parentheses
on top of each other, whereas if we introduce loops and conditionals and
such, these programs get shorter. Because loops and conditionals happen
to match the stuff that our human-written programs need to do...
Loops are evil in most situations.
Let me show you why:
Draw a square using put_pixel(x,y)
// loops are more scalable, but, damage this code anywhere and it can
potentially kill every other process, not just itself. This is why
computers die all the time.
for (int x = 0; x 2; x++)
{
for (int y = 0; y 2; y++)
{
put_pixel(x,y);
}
}
opposed to
/* The below is faster (even on single step instructions), and can be
run in parallel, damage resistant ( ie destroy put_pixel(0,1); and the
rest of the code will still run), is less scalable ( more code is
required for larger operations)
put_pixel(0,0);
put_pixel(0,1);
put_pixel(1,0);
put_pixel(1,1);
The lack of loops in the brain is a fundamental difference between
computers and brains. Think about it. We can't do operations that
require 1,000,000 loop iterations. I wish someone would give me a PHD
Re: [agi] Mechanical Analogy for Neural Operation!
Hi, I pretty much always think of a NN as a physical device. I think the first binary computer was dreamt up with balls going through the system with ball representing 1's and 0's. The idea was written down but never built. Jamming balls that give way at a certain point is the same as using . ie When more than 6 balls jam up, the pressure is released, sending a 1 or a value 6 balls. Addition can be a little different in such systems. ie a value 6 + a value 3 = a value 9. On Sun, 2010-07-11 at 23:02 -0700, Steve Richfield wrote: Everyone has heard about the water analogy for electrical operation. I have a mechanical analogy for neural operation that just might be solid enough to compute at least some characteristics optimally. No, I am NOT proposing building mechanical contraptions, just using the concept to compute neuronal characteristics (or AGI formulas for learning). Suppose neurons were mechanical contraptions, that receive inputs and communicate outputs via mechanical movements. If one or more of the neurons connected to an output of a neuron, can't make sense of a given input given its other inputs, then its mechanism would physically resist the several inputs that didn't make mutual sense because its mechanism would jam, with the resistance possibly coming from some downstream neuron. This would utilize position to resolve opposing forces, e.g. one force being the observed inputs, and the other force being that they don't make sense, suggest some painful outcome, etc. In short, this would enforce the sort of equation over the present formulaic view of neurons (and AGI coding) that I have suggested in past postings may be present, and show that the math may not be all that challenging. Uncertainty would be expressed in stiffness/flexibility, computed limitations would be handled with over-running clutches, etc. Propagation of forces would come close (perfect?) to being able to identify just where in a complex network something should change to learn as efficiently as possible. Once the force concentrates at some point, it then gives, something slips or bends, to unjam the mechanism. Thus, learning is effected. Note that this suggests little difference between forward propagation and backwards propagation, though real-world wet design considerations would clearly prefer fast mechanisms for forward propagation, and compact mechanisms for backwards propagation. Epiphany or mania? Any thoughts? Steve agi | Archives | Modify Your Subscription --- 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=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
[agi] What is the smallest set of operations that can potentially define everything and how do you combine them ?
Hi,
I'm interested in combining the simplest, most derivable operations
( eg operations that cannot be defined by other operations) for creating
seed AGI's. The simplest operations combined in a multitude ways can
form extremely complex patterns, but the underlying logic may be
simple.
I wonder if varying combinations of the smallest set of operations:
{ , memory (= for memory assignment), ==, (a logical way to
combine them), (input, output), () brackets }
can potentially learn and define everything.
Assume all input is from numbers.
We want the smallest set of elements, because less elements mean less
combinations which mean less chance of hitting combinatorial explosion.
helps for generalisation, reducing combinations.
memory(=) is for hash look ups, what should one remember? What can be
discarded?
== This does a comparison between 2 values x == y is 1 if x and y are
exactly the same. Returns 0 if they are not the same.
(a logical way to combine them) Any non-narrow algorithm that reduces
the raw data into a simpler state will do. Philosophically like
Solomonoff Induction. This is the hardest part. What is the most optimal
way of combining the above set of operations?
() brackets are used to order operations.
Conditionals (only if statements) + memory assignment are the only valid
form of logic - ie no loops. Just repeat code if you want loops.
If you think that the set above cannot define everything, then what is
the smallest set of operations that can potentially define everything?
--
Some proofs / Thought experiments :
1) Can , ==, (), and memory define other logical operations like
(AND gate) ?
I propose that x==y==1 defines xy
xy x==y==1
00 = 0 0==0==1 = 0
10 = 0 1==0==1 = 0
01 = 0 0==1==1 = 0
11 = 1 1==1==1 = 1
It means can be completely defined using == therefore is not
one of the smallest possible general concepts. can be potentially
learnt from ==.
-
2) Write a algorithm that can define 1 using only ,==, ().
Multiple answers
a) discrete 1 could use
x == 1
b) continuous 1.0 could use this rule
For those not familiar with C++, ! means not
(x 0.9) !(x 1.1) expanding gives ( getting rid of ! and )
(x 0.9) == ((x 1.1) == 0) == 1note !x can be defined in terms
of == like so x == 0.
(b) is a generalisation, and expansion of the definition of (a) and can
be scaled by changing the values 0.9 and 1.1 to fit what others
would generally define as being 1.
---
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=8660244id_secret=8660244-6e7fb59c
Powered by Listbox: http://www.listbox.com
Re: [agi] Huge Progress on the Core of AGI
On Mon, 2010-06-28 at 13:21 +0100, Mike Tintner wrote: MS: I'm solving this by using an algorithm + exceptions routines. You're saying there are predictable patterns to human and animal behaviour in their activities, (like sports and investing) - and in this instance how humans change tactics? What empirical evidence do you have for this, apart from zero, and over 300 years of scientific failure to produce any such laws or patterns of behaviour? What evidence in the slightest do you have for your algorithm working? Still in the testing phase. It's more complicated than just (algorithm + exceptions), there are multiple levels of accuracy of data and how you combine the multiple levels of data. The evidence to the contrary, that human and animal behaviour, are not predictable is pretty overwhelming. Taking into account the above, how would you mathematically assess the cases for proceeding on the basis that a) living organisms ARE predictable vs b) living organisms are NOT predictable? Roughly about the same as a) you WILL win the lottery vs b) you WON'T win? Actually that is almost certainly being extremely kind - you do have a chance of winning the lottery. -- From: Michael Swan ms...@voyagergaming.com Sent: Monday, June 28, 2010 4:17 AM To: agi agi@v2.listbox.com Subject: Re: [agi] Huge Progress on the Core of AGI On Sun, 2010-06-27 at 19:38 -0400, Ben Goertzel wrote: Humans may use sophisticated tactics to play Pong, but that doesn't mean it's the only way to win Humans use subtle and sophisticated methods to play chess also, right? But Deep Blue still kicks their ass... If the rules of chess changed slightly, without being reprogrammed deep blue sux. And also there is anti deep blue chess. Play chess where you avoid losing and taking pieces for as long as possible to maintain high combination of possible outcomes, and avoid moving pieces in known arrangements. Playing against another human player like this you would more than likely lose. The stock market is another situation where narrow-AI algorithms may already outperform humans ... certainly they outperform all except the very best humans... ... ben g On Sun, Jun 27, 2010 at 7:33 PM, Mike Tintner tint...@blueyonder.co.uk wrote: Oh well that settles it... How do you know then when the opponent has changed his tactics? How do you know when he's switched from a predominantly baseline game say to a net-rushing game? And how do you know when the market has changed from bull to bear or vice versa, and I can start going short or long? Why is there any difference between the tennis market situations? I'm solving this by using an algorithm + exceptions routines. eg Input 100 numbers - write an algorithm that generalises/compresses the input. ans may be (input_is_always 0) // highly general (if fail try exceptions) // exceptions // highly accurate exceptions (input35 == -4) (input75 == -50) .. more generalised exceptions, etc I believe such a system is similar to the way we remember things. eg - We tend to have highly detailed memory for exceptions - we tend to remember things about white whales more than ordinary whales. In fact, there was a news story the other night on a returning white whale in Brisbane, and there are additional laws to stay way from this whale in particular, rather than all whales in general. From: Ben Goertzel Sent: Monday, June 28, 2010 12:03 AM To: agi Subject: Re: [agi] Huge Progress on the Core of AGI Even with the variations you mention, I remain highly confident this is not a difficult problem for narrow-AI machine learning methods -- Ben G On Sun, Jun 27, 2010 at 6:24 PM, Mike Tintner tint...@blueyonder.co.uk wrote: I think you're thinking of a plodding limited-movement classic Pong line. I'm thinking of a line that can like a human player move with varying speed and pauses to more or less any part of its court to hit the ball, and then hit it with varying speed to more or less any part of the opposite court. I think you'll find that bumps up the variables if not unknowns massively. Plus just about every shot exchange presents you with dilemmas of how to place your shot and then move in anticipation of your opponent's return . Remember the object here is to present a would-be AGI with a simple but *unpredictable* object to deal with, reflecting
Re: [agi] A Primary Distinction for an AGI
On Mon, 2010-06-28 at 16:15 +0100, Mike Tintner wrote: That's why Michael can't bear to even contemplate a world in which things and people behave unpredictably. (And Ben can't bear to contemplate a stockmarket that is obviously unpredictable). If he were an artist his instincts would be the opposite - he'd go for the irregular and patchy and unpredictable twists. If he were drawing a box going across a screen, he would have to put some irregularity in omewhere - put in some fits and starts and stops - there's always an irregular twist in the picture or the tale. An artist has to put some surprise and life into what he does - You patternise the things that are patternisable - like an erratic waving arm is still an arm, and it's pattern is erratic. Also, note I used to be a art and animation lecturer for 2 years ;) --- 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=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
Re: [agi] Huge Progress on the Core of AGI
On Sun, 2010-06-27 at 19:38 -0400, Ben Goertzel wrote: Humans may use sophisticated tactics to play Pong, but that doesn't mean it's the only way to win Humans use subtle and sophisticated methods to play chess also, right? But Deep Blue still kicks their ass... If the rules of chess changed slightly, without being reprogrammed deep blue sux. And also there is anti deep blue chess. Play chess where you avoid losing and taking pieces for as long as possible to maintain high combination of possible outcomes, and avoid moving pieces in known arrangements. Playing against another human player like this you would more than likely lose. The stock market is another situation where narrow-AI algorithms may already outperform humans ... certainly they outperform all except the very best humans... ... ben g On Sun, Jun 27, 2010 at 7:33 PM, Mike Tintner tint...@blueyonder.co.uk wrote: Oh well that settles it... How do you know then when the opponent has changed his tactics? How do you know when he's switched from a predominantly baseline game say to a net-rushing game? And how do you know when the market has changed from bull to bear or vice versa, and I can start going short or long? Why is there any difference between the tennis market situations? I'm solving this by using an algorithm + exceptions routines. eg Input 100 numbers - write an algorithm that generalises/compresses the input. ans may be (input_is_always 0) // highly general (if fail try exceptions) // exceptions // highly accurate exceptions (input35 == -4) (input75 == -50) .. more generalised exceptions, etc I believe such a system is similar to the way we remember things. eg - We tend to have highly detailed memory for exceptions - we tend to remember things about white whales more than ordinary whales. In fact, there was a news story the other night on a returning white whale in Brisbane, and there are additional laws to stay way from this whale in particular, rather than all whales in general. From: Ben Goertzel Sent: Monday, June 28, 2010 12:03 AM To: agi Subject: Re: [agi] Huge Progress on the Core of AGI Even with the variations you mention, I remain highly confident this is not a difficult problem for narrow-AI machine learning methods -- Ben G On Sun, Jun 27, 2010 at 6:24 PM, Mike Tintner tint...@blueyonder.co.uk wrote: I think you're thinking of a plodding limited-movement classic Pong line. I'm thinking of a line that can like a human player move with varying speed and pauses to more or less any part of its court to hit the ball, and then hit it with varying speed to more or less any part of the opposite court. I think you'll find that bumps up the variables if not unknowns massively. Plus just about every shot exchange presents you with dilemmas of how to place your shot and then move in anticipation of your opponent's return . Remember the object here is to present a would-be AGI with a simple but *unpredictable* object to deal with, reflecting the realities of there being a great many such objects in the real world - as distinct from Dave's all too predictable objects. The possible weakness of this pong example is that there might at some point cease to be unknowns, as there always are in real world situations, incl tennis. One could always introduce them if necessary - allowing say creative spins on the ball. But I doubt that it will be necessary here for the purposes of anyone like Dave - and v. offhand and with no doubt extreme license this strikes me as not a million miles from a hyper version of the TSP problem, where the towns can move around, and you can't be sure whether they'll be there when you arrive. Or is there an obviously true solution for that problem too? [Very convenient these obviously true solutions]. From: Jim Bromer Sent: Sunday, June 27, 2010 8:53 PM To: agi Subject: Re: [agi] Huge Progress on the Core
Re: [agi] High Frame Rates Reduce Uncertainty
Hi, * AGI should be scalable - More data just mean the potential for more accurate results. * More data can chew up more computation time without a benefit. ie If all you want to do is identify a bird, it's still a bird at 1 fps and 1000 fps. * Don't aim for precision, aim for generality. Eg. AGI KNOWS 1000 objects. If you test to see if your object is a bird, and it is not, you still have 999 possible objects. If you test if it is an animal, you can split your search space in half - you've reduce the possibilities to 500. Successive generalisation produce accuracy, sometimes referred as a hierarchical approach. On Fri, 2010-06-18 at 14:19 -0400, David Jones wrote: I just came up with an awesome idea. I just realized that the brain takes advantage of high frame rates to reduce uncertainty when it is estimating motion. The slower the frame rate, the more uncertainty there is because objects may have traveled too far between images to match with high certainty using simple techniques. So, this made me think, what if the secret to the brain's ability to learn generally stems from this high frame rate trick. What if we made a system that could process even high frame rates than the brain can. By doing this you can reduce the uncertainty of matches very very low (well in my theory so far). If you can do that, then you can learn about the objects in a video, how they move together or separately with very high certainty. You see, matching is the main barrier when learning about objects. But with a very high frame rate, we can use a fast algorithm and could potentially reduce the uncertainty to almost nothing. Once we learn about objects, matching gets easier because now we have training data and experience to take advantage of. In addition, you can also gain knowledge about lighting, color variation, noise, etc. With that knowledge, you can then automatically create a model of the object with extremely high confidence. You will also be able to determine the effects of light and noise on the object's appearance, which will help match the object invariantly in the future. It allows you to determine what is expected and unexpected for the object's appearance with much higher confidence. Pretty cool idea huh? Dave agi | Archives | Modify Your Subscription --- 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=8660244id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
