> > Thanks for the link. I agree that this work is moving > > in an interesting direction, though I'm afraid that for > > AGI (and adaptive systems in general), TM may be too > > low as a level of description --- the conclusions > > obtained in this kind of work may be correct, but not > > constructive enough. > > I'm interested in this sort of work, not to tell me > exactly how to build a system but to give me some way of > cutting down the number of possible systems. Ideally > it would be adopted by the general community, and AI > work might progress more quickly. Hopefully we would > be able to make statements like, "System X only uses a > FSM as the function F that maps the Input i and work > tape memory W on to W and the output tape O, whereas > experiments have shown that some collections of neural > cells can be equivalent to a memory bounded UTM in > expressiveness for F." ....
Hi Will, You may also find this work by Shahaf and Amir, presented at COMMONSENSE 2007 earlier this year, interesting: http://www.ucl.ac.uk/commonsense07/papers/shahaf-and-amir.pdf It is an early paper with a lot of unanswered questions, and I don't believe it is exactly what you have in mind; but I found the work to be a fascinating idea and you might find it to be some useful "food for thought". In summary, their idea is to expand the idea of a Turing machine so that a human being is asked to operate on the tape when the algorithm gets stuck. In that way they can compare AI algorithms and progress towards fully autonomous AI using big-O notation. -Ben ----- 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=59788730-747a5f
