I am not sure what you are saying Nanograte. I can't remember what a schema in AI is other than it might be some kind of partial definition like a set of abstractions that might be filled in with specifics or something like that. And what is the repetitive heuristic algorithm and why does it act as a 2-sided sword? I do think I will need to use hierarchies but not in the sense of a strict traditional logical hierarchy. Jim Bromer
On Tue, Jun 11, 2019 at 1:59 PM Nanograte Knowledge Technologies < [email protected]> wrote: > Jim, I think what you're describing here has relevance for schemas. > However, unless you have the relativist context pegged down, the schemas > remain just schemas in a non-relativist universe. Somehow you'll need to > tie it all together by means of hierarchy. You'll need to think out of the > box some more on this one, until you've solved the repetitive, heuristic > algorithm, which acts as a 2-sided sword. E.g., What if there was a 3rd > supercat who lived in the box with the other 2, one that was immune to > toxins and electricity? > > ------------------------------ > *From:* Jim Bromer <[email protected]> > *Sent:* Tuesday, 11 June 2019 19:32 > *To:* AGI > *Subject:* Re: [agi] Re: A mathematics of concpetual relations? > > Mike, > I again apologize for my strident and aggressive responses. I honestly do > not mean to be disrespectful of the remarks that have been made in this > thread.I just have a way of expressing myself which comes across as a > little rough at times. > > Let me give you an example of something that I just thought about. Suppose > I decided to use humongous numbers - maybe a million bits - but with the > intention only to use a small part of it at a time for any computation. The > bit positions might have some kind of meaning or some directive related to > meaning. Then how can I efficiently represent these huge numbers in which > only tiny disparate bits are relevant? This becomes a traditional > compression problem. So suddenly, just because I am thinking about this in > a special way, the impossible part becomes very possible - given that I > might be able to come up with algorithms that could effectively work on > these compressed numbers without having to decompress them first. This is > an interesting thought. What makes it interesting is that I am not limited > to some mundane application of a tired method like using vectors mapped > onto 3-dimension space using traditional computational arithmetic or > something. The freedom of thinking outside the box, even though it will > usually be unsuccessful, illuminates whole new vistas. > Jim Bromer > > > On Tue, Jun 11, 2019 at 1:23 PM Mike Archbold <[email protected]> wrote: > > mean't "wasn't being dismissive". Typing too fast > > On 6/11/19, Mike Archbold <[email protected]> wrote: > > Jim, It just reminded me of the Gardenfors work -- I was being at all > > dismissive of your posts. I was just pointing the work out in case you > > were not familiar with it. On the whole, I'm not dismissive of > > anybody's ideas in AGI. It's all a wide open space IMO. > > > > On 6/11/19, Jim Bromer <[email protected]> wrote: > >> I remember that someone kept dismissing my notion of conceptual > >> relativism > >> and finally he mentioned some book that had been written 40 or 50 years > >> ago > >> which had mentioned that concepts were relative. I wondered - could it > be > >> true? Could someone have examined conceptual relativism decades ago? I > >> did > >> not find the book that he mentioned but I did find references to it and > I > >> found work that was done by the authors around the time the book was > >> published. The authors mentioned a lot about the fact that concepts are > >> relative and nothing about the notion that concepts are relativistic. It > >> would be tedious of me to go over the difference again, but there is a > >> major difference. The idea that I am talking about something that had > >> been > >> settled and the closed 20 or 50 years ago is dismissive. But it is also > >> amusing because it means you are all chasing the latest fads (which are > >> admittedly making great advances) while leaving the field of my special > >> interests free, open, and unsullied for me. So thank you for not getting > >> it. (I am not being cranky, I really believe that we are representative > >> of > >> the areas of interest that other people are pursuing, some much more > >> effectively than we are, and this mini sampling indicates that there is > >> something here that might be worthwhile for me to examine partly because > >> there is not going to be much competition.) > >> Jim Bromer > >> > >> > >> On Tue, Jun 11, 2019 at 12:54 PM Mike Archbold <[email protected]> > >> wrote: > >> > >>> This topic reminds me of this book from almost 20 years ago: > >>> > >>> https://mitpress.mit.edu/books/conceptual-spaces > >>> > >>> > >>> > >>> On 6/11/19, [email protected] <[email protected]> wrote: > >>> > Generative Neural Networks, GAN. > >>> > This give give a relation from stating image or data to another. > >>> > > >>> > Latent Space Human Face Synthesis | Two Minute Papers #191: > >>> > https://www.youtube.com/watch?v=aR6M0MQBo2w > >>> > > >>> > A programmer select two images or data points. > >>> > A programmer put in 50 percent value into a GAM and train it to be > >>> > 50 > >>> > percent transformation > >>> > between to faces. This 50 percent value is called a "latent value" > >>> > > >>> > Latent value can used for mapping distance in weight space. > >>> > > https://towardsdatascience.com/graduating-in-gans-going-from-understanding-generative-adversarial-networks-to-running-your-own-39804c283399 > >>> > > >>> > The latent value can be used to make movement vectors through weight > >>> > space: > >>> > https://poloclub.github.io/ganlab/ > >>> > > >>> > Unsupervised GAN's are the way of the brain, artificial or real: > >>> > > https://www.academia.edu/37275998/A_Nice_Artificial_General_Intelligence_How_To_Make_A_Nice_Artificial_General_Intelligence > > *Artificial General Intelligence List <https://agi.topicbox.com/latest>* > / AGI / see discussions <https://agi.topicbox.com/groups/agi> + > participants <https://agi.topicbox.com/groups/agi/members> + delivery > options <https://agi.topicbox.com/groups/agi/subscription> Permalink > <https://agi.topicbox.com/groups/agi/T395236743964cb4b-M20e598165dea2b1e293914b2> ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T395236743964cb4b-Md5786cba52661eb565f85bea Delivery options: https://agi.topicbox.com/groups/agi/subscription
