> From: Ed Porter [mailto:[EMAIL PROTECTED] > > But even with a current 32 bit PC with say 4G of Ram you should be able > to > build an AGI that would be a meaningful proof of concept. Lets say 3G > is > for representation, at say 60 bytes per atom (less than my usual 100 > bytes/atom because using 32bit pointers), that would allow you roughly > 50Million atoms. Over 1 million seconds (very roughly two weeks 24/7) > that > would allow an average of 50 atoms a second of representation. Of > course > your short term memory would record at a much higher frequency, and over > time more and more of your representation would go into models rather > than > episodic recording. But as this happened the vocabulary of patterns > would > grow and thus one atom, on average would be able to represent more. > But it seems to me such an AGI should be able to have meaningful world > knowledge about certain simple worlds, or certain simple subparts of the > world. For example, it should be able to have a pretty good model for > the > world of many early video games, such as pong and perhaps even pac-man > (Its > been so long since I've seen pac-man I don't know how complex it is, but > I > am assuming 50 million atoms, many of which, over time, would represent > complex patterns, would be able to catch most of the meaningful > generalizations of pac-man including its control mechanisms and the > results > they occur).
Yes I can imagine this. But how much information would be in each 60 byte atom? Is it a pointer to a pattern stored on disk, or is it some sort of index, or is it a portion of a pattern, or is it a full pattern in a simple pacman type world? > Is I said in an earlier email, if we want AGI-at-Home to catch on it > would > be valuable to think of some sort of application that would either > inspire > through importance or entice by usefulness or amusement to cause people > let > it use a substantial part of their machine cycles. Well I can't elaborate publicly but I actually have this application running, still in pre-alpha mode... ahh.. but I have to sell this thing enabling me to buy R&D time to potentially convert it to a protoAGI...so no open source on that one :( BUT there are many other applications that could be the delivery mechanism. There are a number of ways to do it... one way was discussed earlier where you sell your PC resources. That is a good idea! > You mention an interest in intelligent indexing. Of course, > hierarchical > memory provides a fairly good from of intelligent indexing, in the sense > that it automatically promotes indexing through learned combinations of > indicies, and can be easily made to have probabilistic and importance > weights on its index links to more efficiency allocate index > activations. > > How does your intelligent indexing work? Well I can describe briefly, there are two basic types of virtual indexing, the actual disk based indexing I'm trying to still use a DBMS for that since they do it so well. First type is based on algebraic structure decomposition. I see everything as algebraic structure; an AGI computer can do the same, but way better. When everything is converted to algebraic structure things become very index friendly, in fact so friendly it looks like many things collapse or telescope down. The other type of indexing that I just started working on is CA based universal symbolistic generation/indexing. Algebraic structure is good for "skeltoidal" but you need some filler. CA's seem like they can do the trick. The thing with CA's is that they can be indexed based on uncalculated values. If a CA structure is so darn complex why waste the cycles calculating it? The CA's have infinite symbolistic properties that only a portion of them need be calculated (take up resources). Linking the algebraic structure indexing with CA indexing I'm trying to smooth out with group semiautomata, but a lot of magic still happens there :) So that's it without getting too into details. Very primitive still ... John > > -----Original Message----- > From: John G. Rose [mailto:[EMAIL PROTECTED] > Sent: Tuesday, December 04, 2007 2:17 PM > To: agi@v2.listbox.com > Subject: RE: Hacker intelligence level [WAS Re: [agi] Funding AGI > research] > > > From: Ed Porter [mailto:[EMAIL PROTECTED] > > John, > > > > I am sure there is interesting stuff that can be done. It would be > > interesting just to see what sort of an agi could be made on a PC. > > Yes it would be interesting to see what could be done on a small cluster > of > modern server grade computers. I like to think about the newer Penryn > 45nm, > SSE4, quadcore quadproc servers with lots of FB DDR3 800mhz RAM running > 64 > bit OS (sorry I prefer coding in Windows) using standard gigabit > Ethernet > quad NICs, with solid state drives, and 15,000 RPM SAS for the slower > stuff, > and a take maybe 10 of these servers. There HAS to be enough resource > there > to get some small prototype going. > > And look at next year's 8 core Nehalem procs coming out... > > Interserver messaging should make heavy use of IP multicasting. Then > another > messaging channel with the new USB 3.0... Supposedly USB 3.0 is 4.8 > gigabits. > > > > I would be interested in you Ideas for how to make a powerful AGI > > without a > > vast amount of interconnect. The major schemes I know about for > > reducting > > interconnect involve allocating what interconnect you have to the > links > > with > > the highest probability or importance, varying those measures of > > probability > > and importance in a contest specific way, and being guided by prior > > similar > > experiences. > > Well I actually don't have the theory far enough to calculate > interconnect > metrics. But I try to minimize that through storage structure. What gets > stored, how it gets stored, where it's stored, how systems are modeled, > what > a model is, what a system of models are, how systems of models are > stored,.. > don't store dupes, store diffs... mixing code and data, collapsing data > into > code, what is code and what is data? Basically a lot of intelligent > indexing, like real intelligent indexing... > > I'm working on using CA's as universal symbolistic indexors and > generators - > IOW exploring a theory of uncalculated precalcs for computational > complexity > indexing using CA's in order to control uncertainty and manage > complexity... > > Lots of addicting brain candy stuff... > > John > > > > > > ----- > This list is sponsored by AGIRI: http://www.agiri.org/email > To unsubscribe or change your options, please go to: > http://v2.listbox.com/member/?&; > > ----- > This list is sponsored by AGIRI: http://www.agiri.org/email > To unsubscribe or change your options, please go to: > http://v2.listbox.com/member/?&; ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=71970729-44bbc6
