On 14/02/2008, Mike Tintner <[EMAIL PROTECTED]> wrote: > Pei: > Though many people assume "reasoning" can only been applied to > > > "symbolic" or "linguistic" materials, I'm not convinced yet, nor that > > there is really a separate "imaginative reasoning" --- at least I > > haven't seen a concrete proposal on what it means and why it is > > different. > > > > I suspect - and correct me - that you haven't thought much at all about this > whole area of imaginative and visual reasoning - i.e. how one image is drawn > from another, or how someone delineates a drawing of an object from the > object itself. How, say, do you get from a human face to the distorted > portraits of Modigliani, Picasso, Francis Bacon, Scarfe, or any cartoonist? > By logical or mathematical formulae?
Actually, yes. Computer vision processing has always been based on mathematical formulae. > Which parts of the face do logic or > semantic networks tell you to highlight or leave out or transpose or smudge > or overlay, or what to blur, and what to sharpen? There are many entertainting computer programs that "draw" in an "artistic way", given a snapshot of a face. Its all just math under th covers. > Which of the continuously > changing expressions on a person's face does logic tell you are most > representative of their personality? This is learned over many years. In defense of Pei Wang's NARS, the foundations that he lays down there are broad enough to encompass the mathematics of image processing. When he writes (A->B, B->C) |- A->C in NARSese, don't make the mistake that A,B,C are single-bit true-false values. These can be multi-gigabit structures with all sorts of complexities embedded inside of them, including ideas that "A looks like a smiling face" at the visual level (or symbolic level, or both, including info about what the face might look like in darkness, light, happy or sad, etc..) Also, don't mistake logic and computation. While computers are anchored in boolean logic, they can do gazillions of ops per second; Computer programmers don't push around single bits at a time. And so also in NARSese -- something like (A->B, B->C) |- A->C is one op; yet one might be performing gazillions of these just to recognize one face. There is nothing in the foundations of NARS that prevents "imaginative" reasoning, certainly not based on my understanding. --linas ------------------------------------------- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244&id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com
