On 19/10/2007, John G. Rose <[EMAIL PROTECTED]> wrote: > > From: William Pearson [mailto:[EMAIL PROTECTED] > > Subject: Re: [agi] An AGI Test/Prize > > > > I do not think such things are possible. Any problem that we know > > about and can define, can be solved with a giant look up table, or > > more realistically, calculated by an unlearning TM. Unless you are of > > the opinion that learning is unnecessary for intelligence? In which > > case what you want may be possible. > > > > Any appearance of learning can also be faked by GLUT and unlearning > > TMs, using time as an input. If you want to rigorously define > > intelligence, you will need to look at how the internals change and > > base a definition on that. My current thinking is based on which > > search spaces the system moves through while trying to map input to > > output, and how it makes use of information from the outside to change > > what it does. > > > > Whether or not learning is necessary for intelligence would depend on the > exact definition of it. The minimally intelligent engine would contain > internal information.
We may be misinterpreting each other. What I mean by learning being necessary for intelligence is that a system that cannot learn is not intelligent. Unless you posit some omnipotent, omniscient entity. Not that a system must learn before it becomes intelligent. > What is the minimal internal state it would need to > start with if any? Is the system, before any input, intelligent? I'm not sure what you are getting at here. I am tempted to answer with, "Can a plane, before it has left the ground, fly?" > There could > be a very simple mathematical definition of intelligence. > This is also a bit opaque to me, are you talking about a definition on the ability to solve problems or a mathematical definition of the internal structure/dynamics? One I think possible, the other... not so much. Will Pearson ----- 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=55566331-f84e16
