hi, > One is that I wonder whether it's worth building into Novamente a pre- > set predisposition to distinguish between 'me' and 'not' me.
My guess is that this will emerge pretty simply and naturally. Some external observations will correlate closely with internal sensations (these are the external manifestations of "me") and others will not. And, if external observation Y correlates closely with internal sensation X, and X correlates with internal sensation Z (that may not correlate with any external observation), then Y will come to correlate with Z [through one of a couple cognitive mechanisms]. A cluster of tightly-linked nodes should then emerge, corresponding to "me-ish" things (internal or external) So, if the cognitive mechanisms work as expected (which may require some parameter-tuning as it's a new application context, and the cognitive mechanisms are now tuned for datamining applications), no pre-set predisposition to distinguish me/not-me will be needed.... I think this is a relatively simple unsupervised learning problem, given a reasonable volume of data obtained from spontaneously acting and observing in a (real or simulated) world > I would > start by setting up in 'itch' to discover whether data flowing through > Novamente is sourced from 'outside me' or from 'within me'. The > second 'itch' would be to label data generated outside of 'me' as being > to do with 'me' or to do with 'other'. I think a baby does the latter by > noticing close correlations between internal feelings/intentions and > seeing things happen 'outside' - I send messages to my arms/legs and I > see objects move in a closely correlated way (turns out that as often as > not I see my arms and legs move, etc.). OK, so what I'm saying is that Novamente will do this about the way you hypothesize a baby does it... > Another itch that I imagine you already have built into Novamente is to > try to find closely correlated streams of data - this would tend to speed > the process of creating 'objects' or standard actions. The search for correlations is intrinsic to Novamente cognition, yeah > It might be worth running a few experiments to see if it significantly > speeds up learning for a Novababy to have the 'itches' about 'me' / 'not > me' built in at the start. Well, if it sped things up, it would only be a short-term effect, because after a certain point, this distinction is just gonna be DONE and LEARNED, and then utilizing it will be basically independent of whether it was acquired thru generic cognition or through a specially-programmed "itch" ... > Another thought is about the way you've split leaning into direct > environmental learning, learning to be taught, and then learning > symbolic communication. > > I think learning symbolic communication is inseparable from learnng to > be taught. And direct environmental learning is inseparable from the > precursors to speech. Let me clarify: These aspects of learning are not really separated inside Novamente, they are internally to be carried out by basically the same processes. However, I have separated them from the point of view of thinking about teaching and training Novamente, simply to jog my mind in a productive direction when designing teaching exercises... > A long time ago I picked up at second hand a rather crude notion of the > Piagetian stages of learning. What I absorbed was the notion that > Piaget said that kids must first learn concretely before learning > abstractly. > > This had a surface common sense ring to it, but I've now decided that I > don't at all agree that concrete learning has to preceed abstract > learning. I agree with Piaget, though I think his statement is only true in a statistical sense. Abstractions are generally built up hierarchically, so we have -- concrete observations -- level 1 patterns in observations -- level 2 patterns, in level 1 observations & concrete observations -- level 3 patterns, ... -- etc. Learning level N patterns is only possible once a large body of level N-1 patterns has been mastered. Ascending the hierarchy takes time, because the more abstract the patterns get, the larger the space of possible patterns that must be searched in order to find the correct patterns. (Of course, a mind is not using a dumb search algorithm, the "search" metaphor is just being used for its evocative power.) > So, I think that the process of streaming data into objects and actions > and relationships and characteristics is already a proccess of abstract > learning. Sure -- it's just on a lower level of the hierarchy of abstraction I've just described... > The second reason for thinging that abstract thinking starts very > early in > human babies is that their primary carers are talking to them all the > time - of using highly abstract notions like "I love you", "you georgeous > little thing", "how clever", "oh, don't be messy" etc. etc. The > baby hears > the words (jigsaw puzzle-like at first - ie. a fuzzy set of sounds in > amongst other words they know) and then over time they associate > behaviours, feelings, settings, other known words, etc. that invest these > abstract terms with more and more meaning. But the abstract symbol > comes first and the meaning later. The words are like pegs to hang > meaning on. It's possible for a baby to learn a few abstract concepts early on, but still not be able to manipulate abstractions fluently for a long time thereafter. This is because "concreteness tends to precede abstraction" is a fuzzy/statistical, not absolute rule (like all the Piagetan stages are, in reality) > Given these ways of seeing things, it's not hard to say that 'learning to > learn from a teacher' is already a process of symbolic learning. If a > robot is circling another object and hoping the NovaBaby will realise > that it wants the NovaBaby to go and get the object (or whatever) then > it is teaching symbolic communication. But it's just doing it in a way > that a mute person would teach it or the way that it would have to teach > it to a deaf child. This form of teaching is no less abstract > that the use > of verbal symbols and it is no easier to learn (might even be harder as > the action might not correlate so uniquely to the symbolic meaning that > the teacher is trying to convey). But in practice, it's much harder to build up complex "grammars" using this form of very simple symbolic learning (if you want to call it symbolic) When I called this "iconic" rather than "symbolic", I was using a precise vocabulary drawn from Peircean semiotics. In a looser sense, it's fine to call it "symbolic"... but in Peircean-semiotics terms, I think my usage was correct. > My first child started speaking at 8 months and he was clearly > understanding words long before that - so my guess is that symbolic > reasoning starts very, very early - and that language take-off is more to > do with gaining critical mass of symbols and then later getting the > motor coordination of the voice box to be able to reproduce words than > it is to do with the raw capacity for abstract reasoning or symbolic > communication. Understanding words and uttering short sentences is VERY DIFFERENT from having full linguistic ability. Are you familiar with Derek Bickerton's distinction between language and proto-language? See his books "Language and Species" and (with William Calvin) "Lingua ex Machina." Very deep & interesting stuff. He makes a strong case that the language used by very young children, apes, and pidgin speakers is not "really language" in that it lacks a recursive syntactic structure.... Recursive syntactic structure is a higher level of symbol manipulation, which requires the lower level to emerge, but has qualitative differences, and enables much more flexible expressive power... > The core notion of symbolic communication I would guess starts from > the minute that the child distinguished self from other (ie > there's a need > for a form of communication that goes beyond just having a thought in > one's head). While I agree with your general point, I think it's useful to distinguish a hierarchy such as - iconic communication (which you call simple symbolism) - simple symbolic communication (protolanguage) - full linguistic communication (involving recursive use of syntactic rules) And of course, isolated instances of constructs on a certain level of the hierarchy may long precede real mastery of that level of the hierarchy. > So, I think that the teacher should talk to a NovaBaby from moment > one and that a NovaBaby should be equipped to receive text and send > text messages from moment one. In terms of senbding text, all it > needs is the ability to select and then send sub-strings out of the input > strings that it receives. If the teacher reacts to the random imitative > babble from the NovaBaby then it will probably learning that certain > sub-strings are meaningful in special ways. Yeah, I agree with you in spirit -- maybe not from day one, but from day N where N is pretty early in the learning process... > If in a simulated world the data fed to NovaBabies is already highly > abstracted (the noise to meaning ratio is very low) then NovaBabies > might be able to be very intelligent with a fraction of the computing > power that animals need - since a good proportion of the grey matter of > animals is taken up with the task of abstracting the data from a simply > staggering amount of noise. I think there will be plenty of noise in the simulated environments, though not as much as in a real environment, I agree... > > (Ah well. For somebody who's not an expert in any of this I sure have > plenty of opinions!) Very interesting sort of conversation to be having ;-) I wish we were experimenting with this stuff today... if all goes according to our current schedule (which occasionally happens), we'll be doing this kind of experimentation sometime in mid-2004 ... a long way off, yet somehow time flies, huh? ben ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
