I was just watching Ben's AGI-08 presentation on neural nets (http://video.google.co.uk/videoplay?docid=8672459372566545966) and this does seem like an interesting and novel idea as far as I know. I hope Hugo de Garis was taking notes because that could be something which he might be able to build an architecture around.
The human mind actually doesn't scale all that well (just look at how dysfunctional large corporations or government agencies can become) and most of us have only a small working memory capacity (as in the magical number seven plus or minus one). I wonder whether there are any hyperspherical properties of combinator trees built from neural relays. ------------------------------------------- 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=101455710-f059c4 Powered by Listbox: http://www.listbox.com
