This is interesting on how Hofstadter talks about how the concepts are compressed. Meaning basically they go from lossy to lossless to lossy to lossless were the interweavings of the lossless "nodes" form recursive trees and the loopy self is the continuous attraction of the active nodes foci up the hierarchy away and into itself symmetrically. sounds interesting. I think that's what he means.. Haven't read that book yet, I did read GEB ages ago.
I don't agree though I think insects have more sense of self than Hofstadter alludes. At least from my observance of their behavior which makes me wonder on how they can fit it into such small a network from their brain size. They have little creativity I think but - not sure about the amount of creativity in relation to their intelligence, it could actually be a lot. This is hard to measure. John From: Robert Levy [mailto:[email protected]] Sent: Tuesday, December 17, 2013 6:48 PM To: AGI Subject: Re: [agi] Abstract Creativity The Hofstadter Strange Loop keynote was just posted online, relevant to this discussion: http://www.infoq.com/presentations/strange-loop-keynote On Tue, Dec 17, 2013 at 9:40 AM, Jim Bromer <[email protected]> wrote: On Tue, Dec 17, 2013 at 6:29 AM, John Rose <[email protected]> wrote: > > IMO a "creativity" could be a search through morphisms of experiential computational complexity patterns applied on relatively unrelated patterns correlated through some expressive indicativistic search potential (the best I can articulate verbally). This would only be a portion of what the generally accepted view of what creativity is. So with my little math subset of "creativity" I would not refer to it as that but it would fall under the umbrella. It took me a little while to get that one. Even though you cannot define an ultimate meta function of imagination, it is imagination that can potentially break through the barriers that the lack of ultimate meta-generalizations leave in its void. Using imagination with rational methods (including the use of key structural insights that can leverage incremental learning) are methods that can often be used to transcend the limitations of narrow AI. So, even though early examples of imagination in AI are too primitive to achieve what we think is AGI, they should be powerful enough to demonstrate the potential of their application. I personally think that a program that is able to do some genuine learning would be able to acquire the skills that are necessary to implement variations of the method. The flaw in this opinion is that while it might be easy to create a test that would demonstrate how learning could be used to implement new variations of applied artificial imagination the examples would probably need to be cherry picked out of the morass of ineffectual complexity that such a test would create using current knowledge. So, one opinion is that imaginative creativity is just another AGI problem; given a solution to learning in a complex data environment (and of learning to outwit the subsequent retrieval complexity) then the problems of imaginative creativity would sort themselves out. > My original question though was if an explicit/a priori creativity would need to have an input variable as reference to a self as our human view of creativity is based on a similar search result's (as described above) effectiveness. A "creative" solution to a problem, a "creative" musical composition. Does creativity rely on a relation to a self as possessor and/or observer? Is there a common relationship of creativity across selves without self? That's all that I was thinking about... > I don't believe so. As Robert and I were saying it becomes a "so what" situation -except- for one possibly critical matter. If artificial imagination can be employed without a sense of self, and if a sense of self is implied by AGI then that implies that the imagination can be part of the fundamental solution to AGI (because it is not dependent on the attainment of a critical base for AGI to emerge). If rational methods (narrow AI combined with meta definitions of how they are employed during run time) can be used to filter out a lot of the useless theories and other noise then imagination can be used to further the narrow AI methods. So, my other opinion is that imaginative creativity is part of the solution to the AGI problem. It can exist within a low level of meta awareness and I believe be used to create a higher level of meta awareness that can discern effective actions from ineffective actions. Jim Bromer On Tue, Dec 17, 2013 at 6:29 AM, John Rose <[email protected]> wrote: > > To build an explicit functional creativity you have to go into definitions even if the result is the definition. Even if building an implicit creativity that emerges from an autopoietic self. Or a relativity defined creativity from an observational standpoint. Creativity is relational and a mathematical concept of creativity can subdivided. > > > > IMO a "creativity" could be a search through morphisms of experiential computational complexity patterns applied on relatively unrelated patterns correlated through some expressive indicativistic search potential (the best I can articulate verbally). This would only be a portion of what the generally accepted view of what creativity is. So with my little math subset of "creativity" I would not refer to it as that but it would fall under the umbrella. > > > > My original question though was if an explicit/a priori creativity would need to have an input variable as reference to a self as our human view of creativity is based on a similar search result's (as described above) effectiveness. A "creative" solution to a problem, a "creative" musical composition. Does creativity rely on a relation to a self as possessor and/or observer? Is there a common relationship of creativity across selves without self? That's all that I was thinking about... > > > > John > > > > From: Anastasios Tsiolakidis [mailto:[email protected]] > > > > a bit of an exercise in futility methinks this topic, unless the definition allowed to quickly screen human and machine "culture" for creativity. Since I consider "survival" (of the "selves" you might say, as there is strength in numbers and speciation) as the key driver of intelligence, it follows that the self must be in all equations. Presumably creativity is keeping the self alive and its memes spreading while generating new domains and new sub-domains of activity, cognitive imperialism you might call it, perhaps I was drinking water from a cup and you start flipping and flying glasses and bottles all over the place like Tom Cruise in that movie. If barman skills were 100% showmanship then probably they wouldn't exist, but since you get a bit of a workout too and get your drinks mixed in the process, while partially satisfying the demands of innovation seekers, then you probably have constructive creativity, > > As I have pointed out before, the surviving self is a rather non-computable entity, eternally waltzing towards its own annihilation with little to show for it in the process, so I would not go into definitions and algorithms for the self or its creative side, perhaps after creating the self I have no need for further definitions, it could well be the self has a need for definitions but that is not my problem or yours, is it? > > AT > > AGI | Archives | Modify Your Subscription > > > > AGI | Archives | Modify Your Subscription -- Jim Bromer ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/18769370-bddcdfdc Modify Your Subscription: https://www.listbox.com/member/? <https://www.listbox.com/member/?&;> & Powered by Listbox: http://www.listbox.com AGI | <https://www.listbox.com/member/archive/303/=now> Archives <https://www.listbox.com/member/archive/rss/303/248029-3b178a58> | <https://www.listbox.com/member/?&;> Modify 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-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
