On Wednesday 29 November 2006 17:23, Philip Goetz wrote: > What is a pointer-and-tag record structure, and what's it got to do > with n-dim vectors?
I was using the phrase to cover the typical datastructures representing "objects" or "frames" in standard AI ( and much of mainstream programming) practice. Nothing special. > I still don't know why you talk about using different numbers of > dimensions simultaneously. Seems to me that you can capture these > invariants in whatever dimensionality you choose, so no need to talk > about fractal representations. At the lowest levels I don't get to choose, since the dimensionality is fixed by my input hardware. In that forced representation, the structure of the real world generates fractal shapes. At higher levels, I do want to choose -- and I have to work out which subspaces / transforms of the lower spaces to map into the higher ones. In fact, I can't just do this myself at design time -- the system itself needs to do it in learning new concepts. --Josh ----- 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/?list_id=303