On Wednesday 06 August 2003 14:59, deering wrote: > Arnoud, I don't know how much help this will be considering I am an > amateur, like you. Your AGI system looks good to me. I think we will > find, in time, that many different approaches to AGI will work, though some > may be more efficient than others, and some may be easier for us to > communicate with. Your system is a low level implementation without an > initial high level architecture,
There is the tree structure of the modules. But of course, the system is a tabula rasa, i.e. starts from scratch, and is moulded by perception. which is supposed to emerge through > learning. This may be possible but may require a tremendous amount of > computational resources. I don't know if you have read my own feeble > attempt at AGI but it is complimentary to yours. > http://home.mchsi.com/~deering9/sim_mod.html Mine is a high level > architecture without a low level implementation. If I had the time and > money I might try to integrate them. I don't really believe in detailed high level architectures. The agent must find things out for himself to be really agi. It must start from its raw percepts and abstract (causal) concepts outof it by itself. The system must be very general applicable, so it must not be biased by concepts put in by the designer. Having a detailed high level architecture will probably do that, I suspect. Furthermore I believe in the idea that Hofstadter propagated in his GEB, that the mind uses procedures that are recursively applied to their output. Mine is the abstraction trick. The computation power needed to get from raw data to high level abstract concepts that will enable global planning over long periods, will probable be quite high, I agree. But still, with my algorithm it will, probably, be computationally feasible (with many many Ghzs). > > I'm in the same time crunch you are, wife, child, job. I too have gone > through a Christian phase, just like Holland, and ended up with atheism, > just like you. Although, I don't hold out much hope for your plan to > create a super-intelligence and ask it, "What is the meaning of existence?" > Many different highly intelligent people have come to completely > contradictory conclusions regarding this question and I don't see how > merely increasing the intelligence decreases the number of theories capable > of explaining the observations. I don't see it either, but then again the abilities of the Singularity agi will probably be incomprehensible for human beings like us. It's a shot in the dark. Maybe a singularity agi turning the entire universe into a kind of 'weltgeist' with eternal progress is the answer. I don't expect human life being part of it, only as a memory maybe. It may eliminate some but also add new > ones. Anyway, even though I share your lack of answers, I am not disturbed > by it. I'm thinking that the reason we are here is not intelligent design > or chance, but rather conceptual necessity. The anthropic argument? > > Well, if there is anything the SAG can do to help your AGI project, email > me off-list at [EMAIL PROTECTED] Well, if you could sponsor me for a year ;-) The emails I get from you and others are already a big help. I was a bit isolated with my project. Contact with other people who do similar things is very motivating. Maybe I'll contact you about your and/or my project. There seem to be some similarities in approach. Met vriendelijke groet, Arnoud ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
