Vladimir, On 12/24/08, Vladimir Nesov <[email protected]> wrote: > > On Thu, Dec 25, 2008 at 9:33 AM, Steve Richfield > <[email protected]> wrote: > > > > Any thoughts? > > > > I can't tell this note from nonsense. You need to work on > presentation,
I am having the usual problem that what is "obvious" to me may not be obvious to anyone else. It would help me a LOT if you could be more specific, so I can avoid burying people in paper. if your idea can actually hold some water. If you think > you understand the idea enough to express it as math, by all means do > so, it'll make your own thinking clearer if nothing else. \xAD\xF4 kn * sn = \xAD\xF4 kn * ∫ (∂sn/∂t) ∂t Basic neuron with ∂sn/∂t inputs = \xAD\xF4 ∫ kn * (∂sn/∂t) ∂t OK to include efficacy kn = ∫ \xAD\xF4 kn * (∂sn/∂t) ∂t OK to integrate the overall result ∂(\xAD\xF4 kn * sn)/∂t = \xAD\xF4 kn * (∂sn/∂t) Computing ∂result/∂t for next neuron QED Identical internal functionality of multiplying inputs by efficacies and summing them, produces identical represented results, regardless of whether the signals directly represent "objects" or ∂object/∂t. Does this help? Steve Richfield ------------------------------------------- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=123753653-47f84b Powered by Listbox: http://www.listbox.com
