RE: [agi] To communicate with an AGI - show and tell visual models

2004-10-18 Thread Yan King Yin
I like the idea of using a fundamentally time-savvy representation, and a vector-based representation does that... This is one of the stronger points in Jeff Hawkins' recent book On Intelligence -- he reviews in detail how most human perception, including visual perception, is

RE: [agi] To communicate with an AGI - show and tell visual models

2004-10-18 Thread Ben Goertzel
Hi, Can you explain a bit what is meant by 'vector'? Any high-dimensional datum can be regarded as a vector, or do you mean something specifically temporal? I believe what he is referring to is a vector indicating a linear approximation to the motion through space of a particular object

RE: [agi] To communicate with an AGI - show and tell visual models

2004-10-17 Thread Ben Goertzel
Dave, I like the idea of using a fundamentally time-savvy representation, and a vector-based representation does that... This is one of the stronger points in Jeff Hawkins' recent book On Intelligence -- he reviews in detail how most human perception, including visual perception, is

Re: [agi] To communicate with an AGI - show and tell visual models

2004-10-16 Thread David Hart
Hi, I've thought this type of representation might be most efficiently achieved with a vector-driven internal representation. That is, Novamente's internal construction and representation of such a demonstration model might be done with vectors (animated by schema procedures), using pixels