I im trying to send the message by just typing my comments in your post referred to below. I have been told that will end up shoing your text with a ">" in front of each line. Just in case it doesn't if you view this in rich text you will see my comments underlined.
-----Original Message----- From: a [mailto:[EMAIL PROTECTED] Sent: Saturday, October 13, 2007 9:36 AM To: agi@v2.listbox.com Subject: Re: [agi] The Grounding of Maths Bayesian nets, Copycat, Shruiti, Fair Isaac, and CYC, are a failure, Bayesian and fair Issac are not failures they generate tens or hundreds of millions a dollars a year in economic value. But they are limited. Approaches to reducing such limitations are beginning to arrive. probably because of their lack of grounding. Yes According to Occam's Razor the simplest method of grounding visual images is not words, but vision. Actually evidence indicates the brain uses a gen/comp hierarchical representation built on visual primatives. But yest it makes sense to ground visual things with visual things. I think that people do not notice visual pictures, visual motion and visual text when they read is because they are mostly subconscious. Mathematicians do not realize visual calculations because they do it in their subconscious. My prior post acknowledge as much, but the difference is that I believe for certain types of reasoning non-visual memories, generalizations, and inferences may the the dominant force. There is also auditory memory. You memorize the words purely as sounds by subvocalization and then visualize it on-the-fly. I don't think there is "auditory grounding". Auditory is a simply a method of efficient storage, without translating it into visual. What evidence do you have that auditory memories can not be used for auditory grounding? In fact, without auditory grounding how do you think audio perception would work? You can also memorize the image of text. Then as you "understand" it, you perform OCR. Why can't you just understand it at the level of the words that have been derived from the original reading (or OCRing)of the text. If it is best to store visual information with visual representations, why wouldn't it be best to store verbal information with verbal representations. I am beginning to wonder if you are serious, or just playing with me. ----- 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=53237919-3178f9
