Mike, this time you are right. Yes, it is about transformations. But that's precisely what makes a representation of something invariant: it is conserved under certain transformations. Unfortunately, this is the precise point where you need to start using some Math. You need to say exactly what a representation is, what a transformation is, and why the transformation leaves the representation invariant. Then, you will have an invrep, and you can start working on AGI with it. That is, on a machine
Sergio -----Original Message----- From: Mike Tintner [mailto:[email protected]] Sent: Saturday, July 21, 2012 11:55 AM To: AGI Subject: Re: [agi] Not an invariant representation but.... P.P.S. I think this debate can best be framed as: how can a given conceptualisation/representation of an object be TRANSFORMED to recognize new examples of that object? it's all about *principles of transformation* how can a given representation of a line/square/hat/chair/face be transformed to recognize new examples? ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/18883996-f0d58d57 Modify Your Subscription: https://www.listbox.com/member/?&; d2 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/303/21088071-c97d2393 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968 Powered by Listbox: http://www.listbox.com
