LOL You expect me to spend all that time writing one out for you for such a complex image, just to prove a point? It's simply not worth my time. I know it can be done, whether you get it or not, but it would take me hours to construct by hand, whereas someday I or someone else will write an algorithm to do it automatically in an instant. The simplest but least useful way would be to make a node for each pixel, and add UP, DOWN, LEFT, and RIGHT links connecting each pixel to its neighbors. QED.
A better way would be to group pixels together into fields, fields into parts, parts into objects, and objects into a scene, with the pieces being knitted together through neighbor relations at each level (similar to UP, DOWN, LEFT, and RIGHT, but more diverse), and each piece connected to the whole it belongs to at the next level up via a PART_OF link. So for one small part of the scene, I might have a several greenish fields, labeled with their color and shape, connected together with their juxtaposed neighbors based on their spatial relationship and connected to a node labeled "leaf" via PART_OF links. Repeat this process fractally to build the whole scene/image. Now you have a tree describing the entire image, with the whole scene at the root, and increased levels of detail as depth increases in the image. A) I defined the parts of the image B) I defined the map -- the form/whole as an image. I can reconstruct the whole from the pieces I broke it into Come up with a good, well thought out argument as to why semantic nets can't represent images (and don't come back til your finished). P.S. I have truly fully realised that you simply don’t SEE the capabilities of semantic nets (or data structures in general) – literally have no pictorial understanding of them . Unfortunately, I don't think I'll ever make it clear to you. On Tue, Oct 23, 2012 at 10:14 AM, Mike Tintner <tint...@blueyonder.co.uk>wrote: > Oh jeez Aaron this is such a fundamental question wh. we have been into > loads in previous years. > > No you can’t represent an image in a net – that is visual illiteracy. > > A) you can’t define the parts of an image > B) you can’t define the “map” – the form/whole - that is an image – (incl. > every subwhole) - the moment you define it, you break it into pieces, > and you lose the form. Try putting a map of Italy into a net. > > Give me a net for this (and dont come back till you are finished): > > http://everydaybipolar.files.wordpress.com/2011/09/jungle2.jpg > > P.S. I have truly fully realised that AGI-ers simply don’t SEE the > problem of AGI – literally have no pictorial understanding of it . I think > I’ve worked out how to make it finally clear – but I don’t have time today. > > > *From:* Aaron Hosford <hosfor...@gmail.com> > *Sent:* Tuesday, October 23, 2012 3:59 PM > *To:* AGI <a...@listbox.com> > *Subject:* Re: [agi] Re: Superficiality Produces Misunderstanding - Not > Good Enough > > If semantic nets can't do it, images can't either, because I can represent > an image as a semantic net and vice versa. They're just data formats. Some > are more handy for some purposes, others more handy for others. Semantic > nets are easier to work with when moving back and forth between the > concrete and the abstract, while images are mainly just useful in one of > these realms. So why are images superior? > > On Tue, Oct 23, 2012 at 9:09 AM, Mike Tintner <tint...@blueyonder.co.uk>wrote: > >> CHAIR >> >> ... >> >> It should be able to handle any transformation of the concept, as in >> >> DRAW ME (or POINT TO/RECOGNIZE) A CHAIR IN TWO PIECES –.. >> >> ..SQUASHED >> ..IN PIECES >> -HALF VISIBLE >> ..WITH AN ARM MISSING >> ...WITH NO SEAT >> ..IN POLKA DOTS >> ...WITH RED STRIPES >> >> Concepts are designed for a world of everchanging, everevolving multiform >> objects (and actions). Semantic networks have zero creativity or >> adaptability – are applicable only to a uniform set of objects, (basically >> a database) - and also, crucially, have zero ability to physically >> recognize or interact with the relevant objects. I’ve been into it at >> length recently. You’re the one not paying attention. >> >> The suggestion that networks or similar can handle concepts is completely >> absurd. >> >> This is yet another form of the central problem of AGI, which you clearly >> do not understand – and I’m not trying to be abusive – I’ve been realising >> this again recently – people here are culturally punchdrunk with concepts >> like *concept* and *creativity*, and just don’t understand them in terms of >> AGI. >> >> *From:* Jim Bromer <jimbro...@gmail.com> >> *Sent:* Tuesday, October 23, 2012 2:04 PM >> *To:* AGI <a...@listbox.com> >> *Subject:* Re: [agi] Re: Superficiality Produces Misunderstanding - Not >> Good Enough >> >> Mike Tintner <tint...@blueyonder.co.uk> wrote: >> AI doesn’t handle concepts. >> >> >> Give me one example to prove that AI doesn't handle concepts. >> Jim Bromer >> >> >> >> On Tue, Oct 23, 2012 at 4:24 AM, Mike Tintner >> <tint...@blueyonder.co.uk>wrote: >> >>> Jim: Mike refuses to try to understand what I am saying because he >>> would have to give up his sense of a superior point of view in order to >>> understand it >>> >>> Concepts have nothing to do with semantic networks. >>> AI doesn’t handle concepts. >>> That is the challenge for AGI. >>> The form of concepts is graphics. >>> The referents of concepts are infinite realms.. >>> >>> What are you saying that is relevant to this, or that can challenge this >>> – from any evidence? >>> >>> >>> >>> >>> >>> >>> >>> >>> >>> >>> >>> >>> >>> >>> >>> >>> >>> *AGI* | Archives <https://www.listbox.com/member/archive/303/=now> >>> <https://www.listbox.com/member/archive/rss/303/10561250-164650b2> | >>> 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/303/6952829-59a2eca5> | >> 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/303/23050605-bcb45fb4> | >> 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/303/6952829-59a2eca5> | > 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/303/23050605-bcb45fb4> | > 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/303/21088071-c97d2393 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968 Powered by Listbox: http://www.listbox.com
