Wow. Really? He can't recognize a basic "dog" / "cat" etc? Are you sure?
Then isn't it a nerve to go public & start distributing the Numenta system?
I would have thought that someone with that kind of inventive/innovative
background, would insist on having something solid to build on - like the
capacity to recognize basic types of animals or objects. How about "cups"
which he also features? His sites do seem to imply that he has cracked
these basic problems.
----- Original Message -----
From: "DEREK ZAHN" <[EMAIL PROTECTED]>
To: <[email protected]>
Sent: Thursday, May 03, 2007 4:54 PM
Subject: Re: [agi] The University of Phoenix Test [was: Why do you think
your AGI design will work?]
Mike Tintner writes:
I don't know though - having still only glanced at [Hawkins's] stuff -
whether he has yet made the transition from being able to recognise a
"dog" to being able to recognize an "animal." Anyone know about this?
I'm fairly certain the answer is no -- in fact as far as I know there has
not even been a demonstration of HTM doing dog recognition (or anything
similarly complex). I believe Hawkins would likely say that the
"conceptual"
regularities for an animal concept can and will be discovered by HTM. But
no such demonstration has yet been made.
Hawkins does talk about a fairly general picture-object classifier being a
major
development goal for Numenta.
-----
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/?&;
--
No virus found in this incoming message.
Checked by AVG Free Edition. Version: 7.5.467 / Virus Database:
269.6.2/785 - Release Date: 02/05/2007 14:16
-----
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=231415&user_secret=fabd7936
