Mike, The concept of chair is not an isolated concept by itself. It is also not recognized using a single simple "schema". People have seen many chair instances in their lives and are able to learn their features and affordances. We are able to compare their features and structures.
So, when we see another chair, we are not just comparing a single constructed schema. We compare the features to features we've seen before, we analyze the uses of the structures and how similar they are to other objects we've seen before. What might it be used for? Put just about anything with a concave shape on the floor with 3 or four legs and you can call it a chair. LOL. You see, there are physical features and patterns that are do make it possible to consider that maybe a new object might be a chair, but it is by no means some schema set in stone. We just fine something that works well. And I've given you plenty of ways to think about it that would suggest ways of solving the problem that would work well. So, to say that I must create this perfect schema to prove that AGI is possible is dumb and unreasonable. I can get you a close description of a "schema" that would recognize it. But I certainly cannot write the program out for you. It involves knowledge, which involves lots of supporting algorithms to construct and use. It seems that no matter how much detail I give you, you can't read between the lines. So, give it a rest mike. It is clearly possible to do. How exactly it is done is yet to be determined. This is why I say in my paper it is important to start with raw data, because it is unrealistic and unrepresentative to construct solutions that don't use knowledge and try to solve the problem without the right knowledge. Human beings do not recognize chairs in a vacuum. A lot of knowledge and experience goes into it. Some of the things on your google example images would not be recognized as chairs to people if given out of context. So, to force AI to recognize them all with 100% accuracy is unreasonable. That's why I don't like arguing with you. You are unreasonable and will never admit that you're wrong. Dave On Mon, Aug 9, 2010 at 10:21 AM, Mike Tintner <tint...@blueyonder.co.uk>wrote: > You're somewhat confused here (and now that you're answering, one can see > why & make progress). > > "The use of" or "to use" a chair, involves a physical class of forms - > bottoms or other objects have to make physical contact with - sit on - the > chair/fridge etc. Everything we're talking about is physical and can only be > conceived of physically and, relative to our discussion, visually. > > And you clearly don't see that you have still not identified any kind of > physical schema/ framework for either "chair" or "sitting" or anything > else. > > And that is what a visual AGI must do - use some kind of physical schema - > in order to recognize an object as a "chair" or the action of an object as > "sitting." > > [Note I use "schema"/"framework" rather than "pattern" - the former are > more general terms, the latter much more specific (& mathematical). I > suspect that you may be using "pattern" here confusedly in the > popular/nonmathematical sense wh. is more akin to "schema." But you and all > other AGI-ers actually deal computationally in math. patterns, and it is > that sense that I am addressing]. > > When you claim that there is a pattern to "chair[s]" you are making a > mathematical claim, - and it is completely indefensible. (Show me otherwise, > John). And that is perhaps the most central issue of AGI. So it is worth > consideration. > > You also seem to be confused about my position - wh. BTW as I've pointed > out is backed by at least one significant AGI-er. I am NOT suggesting > conceptualisation/object recognition "cannot" be done - just not done by > your and others' 100%-record-of-failure mathematical methods. (I'm almost > tempted to say a "blind idiot could see that" [image: Smile emoticon] ).** > > I'm suggesting that the brain uses fluid schemas to recognize objects (and > concepts) - fluidly stretchable (and editable) schemas - when we say "by no > stretch of the imagination can that be recognized/classify as a "chair." " - > we are unconsciously indicating the underlying process of object recognition > - one of "stretching" image schemas to match incoming objects. > > If you want an inspirational image of a fluid schema, think "strings" - as > in string theory - those oscillating strings which are supposed to be > capable of making any shape of particle or object. (I'm too ignorant to know > how precisely the brain's image schemas and nature's theoretical string > schemas can be aligned - comments welcome - but there seems to be a loose > aptness and even beauty in the comparison. It would be rather wonderful if > mind and matter are conceived/work on similar principles). > > If you want both evidence and a concrete example of how fluid and > stretchable the brain's schemas can be - think of what the schema must be > like for "one" or "1". Well, something like a line obviously, But what's not > so obvious - although undeniable - is how stretchable and fluid that line > must be in order to recognize diverse objects - as diverse as "one" octopus, > "one" cactus", "one "mountain. See foto below. The brain can stretch a > line outwards to encompass any form of object in the universe - or > conversely, squeeze/stretch any object inwards to form a "1". All those > objects in the foto can be squeezed/stretched into that "one" on the top > left. > > Now is anyone here going to have the gall to tell me that process of object > recognition is mathematical? > > But just as strings are - or could be - central to matter and physics; so > are fluid schemas central to intelligence - and especially to concepts. > > **Correction - a blind idiot *could* see - by touch - that the diverse > forms of one octopus/flower etc could not be reduced to a line by any > mathematical process. > > P.S. When I say that maths cannot deal with fluid schemas and object > recognition, one should perhaps amend that - it may be that no existing form > of maths. wh. deals entirely in "set forms" and patterns can, but that a > creative version of maths, dealing in "free forms" and patchworks, could. > > P.P.S. "String" - the concept - itself involves an extremely fluid schema - > is a variation, in fact, of the schema of "one/1" - and must embrace many > diverse forms that strings may be shaped into. > > > > > *From:* David Jones <davidher...@gmail.com> > *Sent:* Monday, August 09, 2010 2:13 PM > *To:* agi <agi@v2.listbox.com> > *Subject:* Re: [agi] How To Create General AI Draft2 > > Mike, > > Quoting a previous email: > > QUOTE > > In fact, the "chair" patterns you refer to are not strictly physical > patterns. The pattern is based on how the objects can be used, what their > intended uses probably are, and what most common effective uses are. > > So, chairs are objects that are used to sit on. You can identify objects > whose most likely use is for sitting based on experience. > > END QUOTE > > > Even refrigerators can be chairs. If a fridge is in the woods and you're > out there camping, you can sit on it. I could say "sit on that fridge couch > over there". The fact that multiple people can sit on it, makes it possible > to call it a couch. > > But, it's odd to call it a chair, because it's a fridge. So, when the > object has a more "common effective use", as I stated above, it is usually > referred to by that use. If something is most likely used for sitting by a > single person, then it is a chair. If its most common best use is something > else, like cooling food, you would call it a fridge. > > So, maybe the pattern would be, if it has some features like a chair, like > possible arm rests, a soft bottom, cushions, legs, a back rest, etc. and you > can't see it being used as anything else, then maybe it's a chair. If > someone sits on it, it certainly is a chair, if you find it by searching for > chairs, its likely a chair. etc. > > You see, chairs are not simply recognized by their physical structure. > There are multiple ways you can recognize it and it is certainly important > to know that it doesn't seem useful for another task. > > The idea that chairs cannot be recognized because they come in all shapes, > sizes and structures is just wrong. > > Dave > > > On Mon, Aug 9, 2010 at 8:47 AM, Mike Tintner <tint...@blueyonder.co.uk>wrote: > >> Examples of nonphysical patterns? >> >> *From:* David Jones <davidher...@gmail.com> >> *Sent:* Monday, August 09, 2010 1:34 PM >> *To:* agi <agi@v2.listbox.com> >> *Subject:* Re: [agi] How To Create General AI Draft2 >> >> You see. This is precisely why I don't want to argue with Mike anymore. >> "it must be a physical pattern". LOL. Who ever said that patterns must be >> physical? This is exactly why you can't see my point of view. You impose >> unnecessary restrictions on any possible solution when there really are no >> such restrictions. >> >> Dave >> >> On Mon, Aug 9, 2010 at 7:27 AM, Mike Tintner <tint...@blueyonder.co.uk>wrote: >> >>> John:It can be defined mathematically in many ways >>> >>> Try it - crude drawings/jottings/diagrams totally acceptable. See my set >>> of fotos to Dave. >>> >>> (And yes, you're right this is of extreme importance. And no. Dave, there >>> are no such things as "non-physical patterns"). >>> >>> >> *agi* | Archives <https://www.listbox.com/member/archive/303/=now> >> <https://www.listbox.com/member/archive/rss/303/> | >> Modify<https://www.listbox.com/member/?&;>Your Subscription >> <http://www.listbox.com/> >> *agi* | Archives <https://www.listbox.com/member/archive/303/=now> >> <https://www.listbox.com/member/archive/rss/303/> | >> Modify<https://www.listbox.com/member/?&;>Your Subscription >> <http://www.listbox.com/> >> > > *agi* | Archives <https://www.listbox.com/member/archive/303/=now> > <https://www.listbox.com/member/archive/rss/303/> | > Modify<https://www.listbox.com/member/?&;>Your Subscription > <http://www.listbox.com/> > *agi* | Archives <https://www.listbox.com/member/archive/303/=now> > <https://www.listbox.com/member/archive/rss/303/> | > Modify<https://www.listbox.com/member/?&;>Your Subscription > <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=8660244&id_secret=8660244-6e7fb59c Powered by Listbox: http://www.listbox.com
