So where is the difference
There is no difference.

Cool.  That's one vote.

Anyone else want to take up the issue of whether there is a distinction between competent scientific research and competent learning (whether or not both are being done by a machine) and, if so, what that distinction is?

Or how about if I'm bold and follow up with the question of whether there is a distinction between a machine (or other entity) that is capable of competent scientific research/competent generic learning and a general intelligence?

That's an interesting definition of general intelligence that could have an awful lot of power if it's acceptable . . . . .


----- Original Message ----- From: "Matt Mahoney" <[EMAIL PROTECTED]>
To: <agi@v2.listbox.com>
Sent: Saturday, October 25, 2008 5:59 PM
Subject: Re: [agi] If your AGI can't learn to play chess it is no AGI


--- On Sat, 10/25/08, Mark Waser <[EMAIL PROTECTED]> wrote:

> Scientists choose experiments to maximize information
> gain. There is no
> reason that machine learning algorithms couldn't
> do this, but often they don't.

Heh.  I would say that scientists attempt to do this and
machine learning
algorithms should do it.

So where is the difference other than in the quality of
implementation (i.e.
"other than who performs it, of course").

There is no difference. I originally distinguished machine learning because all of the usual algorithms depend on minimizing the complexity of the hypothesis space. For example, we use neural networks with the minimum number of connections to learn the training data because we want to avoid over fitting. Likewise, decision trees and rule learning algorithms like RIPPER try to find the minimum number of rules that fit the data. I knew about clustering algorithms, but not why they worked. I learned all these different strategies for various algorithms in a machine learning course I took, but was unaware of the general principle and the reasoning behind it until I learned about AIXI.

-- Matt Mahoney, [EMAIL PROTECTED]



-------------------------------------------
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/
Modify Your Subscription: https://www.listbox.com/member/?&;
Powered by Listbox: http://www.listbox.com





-------------------------------------------
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=8660244&id_secret=117534816-b15a34
Powered by Listbox: http://www.listbox.com

Reply via email to