[agi] The AGI Test

There's a good chance this topic has been discussed before, so feel free to point the way if that's the case. It's certainly been touched on since I joined the list, but I wanted to break it out for its own sake of discussion. Background: There is a contest that implements the Turing Test for AI

Re: [agi] My proposal for an AGI agenda

On Tuesday 13 March 2007 22:34, Ben Goertzel wrote: > J. Storrs Hall, PhD. wrote: > > On Tuesday 13 March 2007 20:33, Ben Goertzel wrote: > >> I am confused about whether you are proposing a brain model or an AGI > >> design. > > > > I'm working with a brain model for inspiration, but I speculate t

Re: [agi] My proposal for an AGI agenda

J. Storrs Hall, PhD. wrote: On Tuesday 13 March 2007 20:33, Ben Goertzel wrote: I am confused about whether you are proposing a brain model or an AGI design. I'm working with a brain model for inspiration, but I speculate that once we understand what it's doing we can squeeze a few o

Re: [agi] My proposal for an AGI agenda

On Tuesday 13 March 2007 20:33, Ben Goertzel wrote: > I am confused about whether you are proposing a brain model or an AGI > design. I'm working with a brain model for inspiration, but I speculate that once we understand what it's doing we can squeeze a few orders of magnitude optimization out

Re: [agi] Modules; was "My proposal for an AGI agenda"

On Tuesday 13 March 2007 12:53, Eric Baum wrote: > Are you suggesting that there is in no sense a decision made that > there is a new font to be learned (and possibly reserving physical space). Definitely not reserving space. I'm not even sure that the new capability would be in a physically dif

Re: [agi] My proposal for an AGI agenda

I'm working on the assumption that a basic, simple, universal, FAST capability to do analogical quadrature in each module (read: the chunk of brain that owns each concept) working all at once and all together is what can make this possible. I basically agree with this, actually. In N

Re: [agi] My proposal for an AGI agenda

On Tuesday 13 March 2007 15:56, Ben Goertzel wrote: > Without taking a lot of time (maybe I'll elaborate more later), the > point is that humans solve analogy problems not (usually) by finding > specific strong analogies, but by finding a huge number > of weak analogies and statistically polling t

Re: [agi] Logical representation

On 3/13/07, Mark Waser <[EMAIL PROTECTED]> wrote: Hmmm, the dictionary definition of semantic is "of, pertaining to, or arising from the different meanings of words or other symbols" -- which I take to be the *meaning* or *communication* level which certainly can be different from the *working*

Re: [agi] My proposal for an AGI agenda

Hi, Yes, copycat simulated a metric in an ad hoc way, because it lacked a robust way of measuring and utilizing uncertainty... I am unsure (heh heh) what uncertainty has to do with it. CC got a fixed, completely known problem. It could only construct valid interpretations, so there was

Re: [agi] Logical representation

>> I'm inclined to think that on a semantic level they should also use the same >> internal representation Hmmm, the dictionary definition of semantic is "of, pertaining to, or arising from the different meanings of words or other symbols" -- which I take to be the *meaning* or *communication*

Re: [agi] My proposal for an AGI agenda

Aha... we are now getting down to some brass tacks :^) On Tuesday 13 March 2007 12:20, Ben Goertzel wrote: > > Numeric vectors are strictly more powerful as a representation than > > predicates. > > This is not really true... Touché. My "fmult" predicate of a few msgs ago is of course a predicate

Re: [agi] Modules; was "My proposal for an AGI agenda"

Josh> On Tuesday 13 March 2007 07:26, Eric Baum wrote: >> Is there some reason why it is not the most natural thing to look >> at the Helevetica Reader (as with pretty much any proper noun) as >> an instance in the class of font readers? It inherits pretty much >> everything from existing font rea

Re: [agi] Logical representation

On 3/13/07, Mark Waser <[EMAIL PROTECTED]> wrote: Do the many modules have to have one canonical format for representing content -- or do they have to have one canonical format for *communicating* content? I think that you need to resign yourself to the fact that many of the modules are going t

Re: [agi] Logical representation

>> The issue isn't machine time, it's that an AI system consisting of many >> modules has to have one canonical format for representing content, so that >> the modules can work together; so versatility is a key virtue. Do the many modules have to have one canonical format for representing conte

Re: [agi] Logical representation

On 3/13/07, Richard Loosemore <[EMAIL PROTECTED]> wrote: I would cautiously (and with due respect) suggest that IF you have been tempted to categorize this discussion as [Loosemore talking vague nonsense again], you might want to resist that temptation. The "more concrete stuff", when it arrive

Re: [agi] Logical representation

Mark Waser wrote: What have variable names got to do with architecture? Russell is conflating concept names (a.k.a. symbols) and variables. Personally, I would just have the system autonumber each concept as the system generates it and then have some serious resources devoted to determining

Re: [agi] Logical representation

Russell Wallace wrote: Richard: I'm not sure why it's been so extraordinarily difficult to communicate, but from what you're saying here it seems to be back to square one again; continuing to try to communicate in abstract English about this topic doesn't appear to be a productive use of either

Re: [agi] Logical representation

On 3/13/07, Mark Waser <[EMAIL PROTECTED]> wrote: Human-readable is an interesting term . . . . Is a picture human-readable? I think that you would argue not (in this context, obviously). Well, a picture is (in some domains) human-readable - and I think tools that display certain kinds of i

Re: [agi] My proposal for an AGI agenda

Numeric vectors are strictly more powerful as a representation than predicates. This is not really true... A set of vectors is a relation, which is a predicate; I can do any logical operation on them (given, e.g. a term constructor that is simply a hash function along an axis). But they also

Re: [agi] Logical representation

>> The distinction I've been making all along is between human-readable formats >> like predicate calculus, SQL and XML, versus non-human-readable ones like >> vectors of floats, binary machine code, graphs of unlabeled nodes etc. I'm >> arguing for the former (and in particular, for something i

Re: [agi] My proposal for an AGI agenda

On Tuesday 13 March 2007 10:50, Russell Wallace wrote: > On 3/13/07, J. Storrs Hall, PhD. <[EMAIL PROTECTED]> wrote: > >A real working logic-based system that did what > > it needed to would consist mostly of predicates like > > fmult(num(characteristic(Sign1,Bit11,Bit12,...),mantissa(Bitm11,Bitm1

Re: [agi] Logical representation

On 3/13/07, Mark Waser <[EMAIL PROTECTED]> wrote: Russell is conflating concept names (a.k.a. symbols) and variables. And a longer list of other things than I care to enumerate. The distinction I've been making all along is between human-readable formats like predicate calculus, SQL and XML,

Re: [agi] My proposal for an AGI agenda

On Tuesday 13 March 2007 09:41, Ben Goertzel wrote: > One of my questions regarding your approach is why you think that > similar numeric representations are also natural > and efficient for more abstracts sorts of data processing. I think that once you have symbols, there are lots of cool things

Re: [agi] Logical representation

What have variable names got to do with architecture? Russell is conflating concept names (a.k.a. symbols) and variables. Personally, I would just have the system autonumber each concept as the system generates it and then have some serious resources devoted to determining and maintaining a s

Re: [agi] Logical representation

Richard: I'm not sure why it's been so extraordinarily difficult to communicate, but from what you're saying here it seems to be back to square one again; continuing to try to communicate in abstract English about this topic doesn't appear to be a productive use of either of our time at this point

Re: [agi] Modules; was "My proposal for an AGI agenda"

"Object-oriented programming is an exceptionally bad idea which could only have originated in California." - Edsger Dijkstra Eh, the old arguments ... let's at least give a voice to the defense. http://video.google.com/videoplay?docid=-2950949730059754521 - lk - This list is sponsored

Re: [agi] Logical representation

Russell Wallace wrote: On 3/13/07, *Richard Loosemore* <[EMAIL PROTECTED] > wrote: Good god no. It *is* the program. It is the architecture of an AI. So it is part of the AI then, like I said. Regarding the use of readable names. The atomic units of knowl

Re: [agi] My proposal for an AGI agenda

On 3/13/07, J. Storrs Hall, PhD. <[EMAIL PROTECTED]> wrote: But the bottom line problem for using FOPC (or whatever) to represent the world is not that it's computationally incapable of it -- it's Turing complete, after all -- but that it's seductively easy to write propositions with symbols tha

Re: [agi] Logical representation

On 3/13/07, Richard Loosemore <[EMAIL PROTECTED]> wrote: Good god no. It *is* the program. It is the architecture of an AI. So it is part of the AI then, like I said. Regarding the use of readable names. The atomic units of knowledge in the resulting system (the symbols, concepts, logica

Re: [agi] Logical representation

Russell Wallace wrote: On 3/12/07, *Richard Loosemore* <[EMAIL PROTECTED] > wrote: I'm still not quite sure if what I said came across clearly, because some of what you just said is so far away from what I intended that I have to make some kind of response.

Re: [agi] My proposal for an AGI agenda

But the bottom line problem for using FOPC (or whatever) to represent the world is not that it's computationally incapable of it -- it's Turing complete, after all -- but that it's seductively easy to write propositions with symbols that are English words and fool yourself into thinking you've

Re: [agi] Modules; was "My proposal for an AGI agenda"

On Tuesday 13 March 2007 07:26, Eric Baum wrote: > Is there some reason why it is not the most natural thing > to look at the Helevetica Reader (as with pretty much any proper > noun) as an instance in the > class of font readers? It inherits pretty much everything from > existing font readers, exc

Re: [agi] The "Reading Helvetica" Problem

There's at least high-level evidence that there are qualitative differences between low-level vision and general cognition, enough for people like Fodor to base entire philosophies of mind on opaqueness and modularity. Luckily for us humans, we don't have to learn the elements of vision at the

Re: [agi] My proposal for an AGI agenda

On Tuesday 13 March 2007 01:41, YKY (Yan King Yin) wrote: > In my approach, "John loves Mary" can be represented as P(loves,john,mary), > where P is some generic predicate. Each of those terms ("loves", "john" > and "mary") is defined by lower-level terms. I don't see any problem with > this app

Re: [agi] Modules; was "My proposal for an AGI agenda"

Josh> On Monday 12 March 2007 09:01, Richard Loosemore wrote: >> The word "module" has implications, some of which I don't think you >> really want to buy. If the helvetica-reading module is completely >> different from the roman-reading module, why do I find it so easy >> to accommodate to a new

Re: [agi] The "Reading Helvetica" Problem

On 3/13/07, Bob Mottram <[EMAIL PROTECTED]> wrote: Early stage vision involves the detection of primitive types of geometry - edges, lines of different orientation, blobs, corners, colours and motion in different directions. These seem to arise from simple self-organisation due to the physical

Re: [agi] The "Reading Helvetica" Problem

Early stage vision involves the detection of primitive types of geometry - edges, lines of different orientation, blobs, corners, colours and motion in different directions. These seem to arise from simple self-organisation due to the physical properties of neurons and architecture of receptive f

Re: [agi] The "Reading Helvetica" Problem

On 3/13/07, Chuck Esterbrook <[EMAIL PROTECTED]> wrote: When your AGI sees "A" for the first time(s) in Helvetica and learns rules to recognize Helvetica A, then it only has rules for Helvetica A. As opposed to having rules for A in general and rules for A in Helvetica. When Times Roman Italic A