It's like this: You have an associative memory designed to fill in missing contextual details. It basically works by identifying rules and correlations in the inputs, and then extrapolating those and applying them to future inputs to fill in the gaps. Now you throw in an input that is either an observed input that has been mutated randomly, or a randomly generated input, and see how the associative memory fills in the gaps for the randomized input.
Let's look at an example, so we can get away from the vague and generic language. Suppose you know all about cars from real world experience, and so you have learned that they have four wheels placed near the corners, that there is a front and a back, that there is a driver, that there are windows and mirrors so the driver can see, that there is an engine, etc. Now, I ask you to imagine something you have never experienced before (a randomized input/counterfactual claim): What would a car with 5 wheels be like? We could actually have a debate about how such a vehicle would work, arguing over the likely placement of the fifth wheel, whether the other four wheels' placements would be affected, and other design constraints. Other aspects we would likely all agree on without any debate or discussion; we would automatically make the exact same assumptions and generalizations. We would assume the car still had an engine, that it still had a front and back, that there is a driver, that there are windows and mirrors for the driver to see, there is an engine, etc. If anyone tried to say that having a fifth wheel caused these other things to change, we would argue with them unless they could provide a compelling link to having a fifth wheel, and if none could be provided, we would disagree and say they were wrong. Let me say this again, in other words: We would be making strong statements as to the factuality or counterfactuality of claims made about something that *does not exist*. (Yes, yes, there probably is such a car out there, but that's irrelevant as long as the people discussing it have never seen or heard about it.) The reason we can have an actual debate about the characteristics of an imaginary object goes back to the first paragraph. We have observed rules and correlations in *real *objects, and then we apply them to a scenario in which a one or more well-defined counterfactual claims have been made. Then, we proceed as if nothing is amiss, and require all further analysis to be "reasonable", despite our strange starting point. This is the process of filling in the gaps by using an advanced associative memory. *To be creative is simply this: Take the observed rules and correlations of a system, and intentionally break one or more of them. Then see how everything else reasonably shifts to accommodate these unusual points.* I have read (and observed through personal experience) that the most creative moments are those just before falling asleep and just after waking up. I also get extremely creative when sleep deprived, provided I am not too tired to think at all. Given the somewhat random quality of the dream state, and the scrambling of thoughts when sleep deprived, this seems to fit well with the creative process as I have described it. A randomization in my thought processes produces an unexpected counterfactual hypothesis, and then I attempt to reconcile this hypothesis with what I know to be true. This can be done intentionally, too, by asking "What if?" questions. (What if clouds were green? What if the universe were like a Mobius strip? What if we had a word for the overwhelming urge to count things? What if chairs were all cushion and had no legs or backs? What if we could keep chopping a shape into smaller and smaller pieces to estimate its area, without ever stopping? What if computer viruses had a counterpart in biological brains? What if intelligence and creativity could be programmed into a computer and not just observed in human minds? How would things work then?) There are other ways to be creative, but they all, to my knowledge, depend on this idea of filling in the gaps of a counterfactual hypothesis with reasonable assumptions based on previous observations. For example, I like to take two completely unrelated systems, make an arbitrary analogy between them, and then see what comes out. Occasionally the analogy can be resolved reasonably, and I come out with a valuable insight or idea. (Compare capitalism to reinforcement learning. Money = reward. They are both distributed learning algorithms! How can I apply knowledge about each to the other through this analogy?) On Thu, Dec 26, 2013 at 8:39 AM, John Rose <johnr...@polyplexic.com> wrote: > I think imagination is about deconstructing rules. Unravelling and > reravelling concepts, allowing them to operate without or with different > constrictions. Imagination and dreaming that is. > > > > You can arrive at creativity via different means, I think it can just be > explicitly defined on how it operates even how it operates generally. Like > specifying an explicitly functional and operative descriptive complexity of > creativity. Or “a” creativity, like you say could be done via mutation, > differentiation and integration if those operative concepts were explicitly > and functionally described. > > > > John > > > > *From:* Piaget Modeler [mailto:piagetmode...@hotmail.com] > *Sent:* Tuesday, December 24, 2013 12:47 PM > *To:* AGI > > *Subject:* RE: [agi] Abstract Creativity > > > > What we call imagination might simply be mental simulation. Playing > through plan > > steps in ones mind. Creativity might be simple mental operations such as > mutation, > > differentiation, integration. Could be very simple processes at work. > > > > ~PM > > > > > From: johnr...@polyplexic.com > > To: a...@listbox.com > > Subject: RE: [agi] Abstract Creativity > > Date: Tue, 24 Dec 2013 07:58:22 -0500 > > > > I think it is easier in attempting to create AGI with a sense of self. > The > > references to self do begin externally to the AGI. You can explicitly > > attempt to exclude self perhaps for safety reasons? I do think creativity > > and imagination can be accomplished without this self-reference, without > a > > centered self. Ultimately one could say all intelligent beings have > > reference to an omnipresent self. But what does a "hierarchical" or > > amplified self-awareness bring verses merely a pointer to oneself? > > > > An imagination needs to be generated and be experienced. "Imagination" is > > another one of those terms that we borrow from the human experience and > we > > can try to fit into a design for AGI. So we immediately conclude > imagination > > and creativity go hand in hand. > > > > John > > > > -----Original Message----- > > From: Jim Bromer [mailto:jimbro...@gmail.com <jimbro...@gmail.com>] > > Sent: Monday, December 23, 2013 7:10 AM > > To: AGI > > Subject: Re: [agi] Abstract Creativity > > > > I just read an article in Scientific American Mind that mentioned that > > talking to yourself (which is something that just about all people do) > > creates a sense of self. It is a way of creating your own narrative. > > I really did not think that a sense of self was necessary for an AI/AGI > > program to employ imagination and creativity. But even so, it still > might be > > an inescapable effect of imagination and creativity. > > There is a question of whether it is a good idea to try to write a > program > > with some sense-of-self features or not. For instance, in my model of > using > > context-free expressions in order to get a foothold in teaching an AGI > > program some fundamental idea, I foresee that a few elements of language > > could be used to denote some basic database operation. These elementary > > instructions would be learned, not programmed, but they would tend to > become > > associated with certain kinds of operations that were programmed. In this > > way, more sophisticated language could be associated with systems of > > thought. > > These artificial thought processes would include the power to integrate > new > > ideas into previously learned systems of ideas and so on. So the > question is > > whether fundamental operations that refer to the self at an abstract > level > > should be programmed or whether the operations of artificial thought > should > > only be considered to be objective functions. Should the use of the > > imagination be seen as an operation that is inescapably associated with a > > primitive sense of self or should that sense of self develop as a > by-product > > of thought? > > > > Jim Bromer > > > > On Mon, Dec 23, 2013 at 5:12 AM, John Rose <johnr...@polyplexic.com> > wrote: > > > IMO creativity has to do with the confidence in estimating the expense > > > of implementing a rationality to imaginary concepts from experience. > > > > > > Does a concept of self involve experience? I think so. A self forms > > > over time. > > > > > > Creativity is applied, it has rules, otherwise it's imagination. > > > > > > Though, you can create a creativity but that might just be an > > > extension of another self - the creator. To originate a creativity I > think > > requires self. > > > > > > At least that's how I think today from a very simplistic viewpoint :) > > > > > > A general creativity would be then to be able to apply this abstractly > > > with an abstract imagination. Then instance it. Instancing might mean > > > going lower in conceptual hierarchy. Abstract creativity though isn't > > > just going higher into the hierarchy. It's something different I > > > think... A general creativity might not require self whereas a > > > specific creativity might? These are just thoughts... > > > > > > John > > > > > > -----Original Message----- > > > From: Jim Bromer [mailto:jimbro...@gmail.com <jimbro...@gmail.com>] > > > Sent: Tuesday, December 17, 2013 12:41 PM > > > To: AGI > > > Subject: Re: [agi] Abstract Creativity > > > > > > On Tue, Dec 17, 2013 at 6:29 AM, John Rose <johnr...@polyplexic.com> > > 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 <johnr...@polyplexic.com> > > 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:sokratis...@gmail.com<sokratis...@gmail.com> > ] > > >> > > >> > > >> > > >> 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/303/248029-3b178a58 > > > 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/303/24379807-f5817f28 > > > Modify Your Subscription: https://www.listbox.com/member/?&; Powered > by > > > Listbox: http://www.listbox.com > > > > > > > > -- > > Jim Bromer > > > > > > ------------------------------------------- > > AGI > > Archives: https://www.listbox.com/member/archive/303/=now > > RSS Feed: https://www.listbox.com/member/archive/rss/303/248029-3b178a58 > > 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/303/19999924-4a978ccc > > 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> > <https://www.listbox.com/member/archive/rss/303/248029-3b178a58>| > 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/303/23050605-2da819ff> | > 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-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
