Mike, I think the concept of image schema is a very good one.
Among my many computer drawings are ones showing multiple simplified drawings of different, but at different semantic levels, similar events for the purpose of helping me to understand how a system can naturally extract appropriate generalizations from such images. For example, multiple different types of "hitting:". Balls hitting balls. Ball hitting walls. Bats hitting balls. Multiple pictures of Harry hitting Bill and Bill hitting Harry. Etc. So you are preaching to the choir. I have no idea how new the idea is. When Schank was talking about scripts I have a hunch the types of computers he had couldn't even begin to do the level of image recognition necessary do the type of generalization I think we are both interested in. The Serre article, a link to which I sent you earlier today, and the hierarchical memory architecture it provides an example of, make such automatic generalization from images much easier. So learning directly from video, to the extent it is not already here (and some surprising forms of it are already here), will be coming soon, and that learning will definitely include things you could properly call image schemas. Edward W. Porter Porter & Associates 24 String Bridge S12 Exeter, NH 03833 (617) 494-1722 Fax (617) 494-1822 [EMAIL PROTECTED] -----Original Message----- From: Mike Tintner [mailto:[EMAIL PROTECTED] Sent: Thursday, October 04, 2007 4:03 PM To: agi@v2.listbox.com Subject: Re: [agi] breaking the small hardware mindset Edward You talk about the Cohen article I quoted as perhaps leading to a major > paradigm shift, but actually much of its central thrust is similar to > ideas that have been around for decades. Cohens gists are > surprisingly similar to the scripts Schank was talking about circa > 1980. Josh: And his "static image schemas" are Minsky's frames. No doubt. But image schemas, as used by the school of Lakoff/Johnson/Turner/Fauconnier, are definitely a significant step towards a major paradigm shift in cognitive science - are very influential in cognitive linguistics, have helped found cognitive semantics - and are backed by an evergrowing body of experimental science. So that's why I was just a little (and definitely no more) excited by seeing them being used in AGI, however inadequately. I had already casually predicted elsewhere that they would be influential, and I think you'll see more of them. Neither Minsky nor any other AGI person, to my knowledge, uses image schemas as set out by Mark Johnson in "The Body in the Mind" - or could do, if my understanding is correct, on digital computers. ----- 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/?&; ----- 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=50135051-e3911e
