The difference between nondeterministic computation and deterministic computation is a source of random numbers. Its a deep question in CS theory whether this makes any difference-- or whether you can simulate a nondeterministic computation using a pseudorandom number generator. The difference is very subtle though, and of extremely dubious importance to modeling thought. The difference is whether some algorithm will have different worst case properties-- using an appropriate pseudo random number generator would almost always be just as good, but might not be as good in very rare worst case situations. Its hard to see how this is important for thought.
I have no fundamental problem with the brain being a non-deterministic computer, accessing true quantum random bits. I don't believe it works that way, that the physics suggests this or the CS suggests it would make a difference, but I'm open to the idea. However this is explicitly rejected by most philosophers who believe in some fundamental notion of free will, as being insufficient to capture their notion of free will. I claim non-determinism is possible, but something *more* than non-determinism is not definable, they wouldn't know it if they saw it, and their calls for it simply represent a lack of understanding of the nature of computation. They want something inscrutable to happen at the moment of decision where free will is exercised-- but don't understand that the operation of a Turing machine, although reducible to simple steps, is in the whole as inscrutable as could be asked for. Certainly, for modelling purposes, it may well be fruitful to think about the mind as running a non-deterministic program. I'm all in favor of that. Definitely, when building your AGI, think in terms of randomized algorithms! (Then run it using a good pseudo-random no generator if you like.) Mike> Eric: "I claim that it is the very fact that you are making Mike> decisions about whether to supress pain for higher goals that is Mike> the reason you are conscious of pain. Your consciousness is the Mike> computation of a top-level decision making module (or perhaps Mike> system). If you were not making decisions waying (nuanced) pain Mike> against higher goals, you would not be conscious of the pain." Mike> Sure, emotions are designed to pressure the conscious self. But Mike> that whole setup makes no sense at all, if the conscious self is Mike> merely the execution of a deterministic program. It's a) Mike> unnecessary - deterministically programmed computers work Mike> perfectly well without having a conscious, executive self, and Mike> b) it's sadistic in the extreme, torturing and punishing a self Mike> which has supposedly gotta do what it's gotta do anyway. It's Mike> quite bizarre in fact. The conscious self is just the top decision level of the program. The qualia is necessary for the kind of decisions being made. It is in fact the act of the decision making. As to whether its sadistic, the question is bizarly anthropomorphic. It just is. The programming was created by evolution, which doesn't care about sadism. However, I would claim it's not sadistic, its wonderful. Would you rather be a zombie, or feel for several decades like you have joy and pain? Mike> Hence Fodor: Mike> It's been increasingly clear, since Freud, that psychological Mike> processes of great complexity can be unconscious. The question Mike> then arises: what does consciousness add to what unconsciousness Mike> can achieve? To put it another way, what mental processes are Mike> there that can be performed only because the mind is conscious, Mike> and what does consciousness contribute to their performance? Mike> Nobody has an answer to this question for any mental process Mike> whatever. As far as anybody knows, anything that our conscious Mike> minds do, they could do just as well if they were Mike> unconscious. Why then did God bother to make consciousness. What Mike> on earth could he have had in mind? Jerry Fodor, article, You Mike> can't argue with a novel, London Review of Books, 4.3.2004 Well, obviously I have an answer, so Fodor is wrong on his face ;^) But I think the question is somewhat confused. Consciousness is just the level of computation we can report. Most of the computation is unaware, because its hidden by astraction boundaries. The nature of the qualia is equivalent to the code being run. Ours happens to be very rich, because we have powerful programs crafted by evolution so we can make complex decisions correctly. Mike> On the other hand, if the self is nondeterministically Mike> programmed, then everything makes sense. Then the system needs Mike> to pressure a continually wayward self, that keeps getting Mike> carried away on particular tasks , reminding it with emotions of Mike> the other goals and tasks it's ignoring. Back to work. Back to Mike> sleep. Or back to sex. Nondeterminism is a red-herring here, as explained above. Why does it matter if the computation sees true random bits or pseudo-random bits, no doubt generated by the analog physical process in such a way as to be amazingly good pseudo-random bits, but ultimately predictable if you knew the exact physical state of the universe? Who could possibly care? Mike> ----- This list is sponsored by AGIRI: Mike> http://www.agiri.org/email To unsubscribe or change your Mike> options, please go to: Mike> 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=231415&user_secret=e9e40a7e
