2008/3/26 William Pearson <[EMAIL PROTECTED]>: > On 25/03/2008, Vladimir Nesov <[EMAIL PROTECTED]> wrote > > > > Simple systems can be computationally universal, so it's not an issue > > in itself. On the other hand, no learning algorithm is universal, > > there are always distributions that given algorithms will learn > > miserably. The problem is to find a learning algorithm/representation > > that has the right kind of bias to implement human-like performance. > > First a riddle: What can be all learning algorithms, but is none?
--------Excellent philosophical point!! > > Okay simple systems can be computationally universal, > but what does that really mean. > > Computational universality means to be able to represent any > computable function, the range and domain of this function are assumed > to be from the natural numbers to itself. > -------I think Godel would disagree. > > Most AI formulations when they say that are computationally universal > are only talking about function of F: I → O where I is the input and O > is the output. These include the formulations of neural networks/GA > etc that I have seen. However there are lots of interesting programs > in computers that do not map the input to the output. Humans also do > not just map the input to the output, we also think, ruminate, model > and remember. This does not affect the range of functions from the > input to the output, but it does change how quickly they can be moved > between. What I am interested in is in systems where the ranges and > domains of the functions are entities inside the system. > > That is the F: I → S, F: S → O, and F: S→ S are important and should > be potentially computationally universal. Where S is the internal > memory of the system. This allows the system to be all possible > learning algorithms (although only one at any time), but also it is no > algorithm (else F: I x S → S, would be fixed). > > General purpose desktop computers are these kinds of systems. If they > weren't how else could we implement any type of learning system on > them? Thus the answer to my riddle. > > The question I have been trying to answer precisely is how to govern > these sorts of systems so they roughly do what you want, without you > having to give precise instructions. > > Will Pearson -----I am going to read this more carefully later. However, the first part of the answer to your last question is that the governance of these kinds of systems will be based on general rules (or methods of generality) so you do not need to define all the precise instructions that would be needed. But, there is not one level of universality, there are potentially infinite levels of generalization, and they do not all mesh together perfectly. Although this kind of talk may not solve the problem, I believe that this is where we are going to end up working if we continue to work on the problem Jim Bromer ------------------------------------------- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244&id_secret=98558129-0bdb63 Powered by Listbox: http://www.listbox.com
