Re: The skill of learning skills.

Lester Zick wrote: 
On Mon, 02 Jan 2006 01:08:09 GMT, Risujin <risujin@xxxxxxxxxxx> in
comp.ai.philosophy wrote:

JGCASEY wrote: 
So maybe it is more than just adding skills, maybe
it is adding a particular type of skill. Maybe a
skill for adding skills? That is the ability to learn
how to do things all by itself as a result of some
internal needs and experience with its "world".

If we define intelligence as the skill of learning skills, we arrive at a gradual definition for intelligence. It is easy to see how a system may be capable of learning some kinds of skills but not others. The breadth/variety of learnable skills and their relevance to achieving the program's goal determines the degree of intelligence.

Now we need to define a skill, skill variety, and what exactly we mean by learning a skill. If we think of a skill as a state operator...:

* A skill is a procedure for inducing something to transition from one state to another. In other words, a set of instructions which the system is capable of following that predictably produces certain changes in the environment.

* A skill can be of any level of coarseness. We don't necessarily need to specify every action in detail. We can imagine abstract skills such as "drive a car" and reason with them without referring to sub-skills ("start the car").

* The definition of having learned a skill is trivial in this case--either the system can or cannot carry out the procedure. We don't necessarily need to constrain how the system carries out or acquires procedures.

* The power of a system can be measured in terms of the range of goals it is capable of achieving compared with the theoretical range of goals a system with the same inputs/outputs could possibly achieve.

* The intelligence of a system can be measured in terms of the range of skills it is capable of acquiring compared to the range of skills theoretically possible for it to perform. The intelligence of a system is its capacity for increasing its power over the environment.

Curiously, with this definition a static skill set would imply that the intelligence of a system decreases as its power increases. Only learning skills which expand the potential skill set of a system increase its intelligence.

An intelligent system would only require processing power to match human intelligence for time-constrained tasks. If we limit the domain of problems to non-timed goals, there is no reason at least a marginally intelligent system could not be built on a home PC today. 

You know, Risujin, let me run something by you here. Let's assume for
the sake of argument that you have a pretty good insight into what's
wrong with contemporary academic approaches to intelligence. And
you others are motivated by goodness and the search for mechanical
explanations of intelligence.

So you begin by guessing at some solution. Now the problem is not that
you begin by guessing because all we can do is guess at the beginning.
The problem is that instead of demonstrating that your "skill" in fact
represents the general solution to intelligence, you simply define it
and then go off and systematize it as if you had already demonstrated
it. Then you will subsequently become embroiled in endless arguments
with those who disagree.

Maybe I should've made it more explicit but I wasn't actually going for a mechanical or any other kind of solution to the general intelligence problem. If you read carefully, the skills system I proposed falls far short of defining a mechanism. What I was suggesting is instead a possible measure of intelligence as an alternative to "we'll know it when we see it".

There is no argument that "skill" represents a necessary component
of intelligence only whether it is intelligence regardless of how it's
defined. You say it is; others say it isn't that "timing" is much more
basic or environmental manipulation.

I don't say this to discourage you from guessing only to suggest that
what you should be guessing at is how to prove whatever it is you may
guess is the solution to intelligence in mechanical terms. And to me
that means showing alternatives to whatever you guess at are wrong.
And that means showing that alternatives are self contradictory. Then
you'll have something definitive to hang your hat on besides endless
arguments and speculation.

A mechanism for producing/conforming to the behavior I describe above is the ultimate goal here but I'm not claiming to have anything remotely close to it now.

-- Risujin
.

Relevant Pages

  • Re: Intelligence - one of degree?
    ... >> anything that achieves goals isn't exactly behaving ... I tend to more think that the thermostat isn't ... A super skill. ...
    (comp.ai.philosophy)
  • Re: The skill of learning skills.
    ... >> it is adding a particular type of skill. ... >it is capable of achieving compared with the theoretical range of goals ... >is its capacity for increasing its power over the environment. ... So you begin by guessing at some solution. ...
    (comp.ai.philosophy)
  • The skill of learning skills.
    ... it is adding a particular type of skill. ... * The power of a system can be measured in terms of the range of goals it is capable of achieving compared with the theoretical range of goals ... The intelligence of a system is its capacity for increasing its power over the environment. ... with this definition a static skill set would imply that the intelligence of a system decreases as its power increases. ...
    (comp.ai.philosophy)
  • Re: ORICHALCUM UNIVERSE: Updated House Psi Modifications...
    ... the Luck OR Unluck Advantage/Disadvantage _might_ be a latent psion ... This is the Psionic Power of bodily ... prereq Autohealing at Skill 10 or better): ... Infliction is the polar opposite of Healing, ...
    (rec.games.frp.gurps)
  • Re: Tai Chi Theory (for knotbinder)
    ... And they ascribe the skill to 'chi'. ... the power gained via the use of leverage to some unknown force. ... your fellow students falling all over themselves to some unknown ... bad injuries to students by accident or to test the skill. ...
    (rec.martial-arts)