> Hi Yan, > > You may want to look into the work of David A Arathorn > in this regard. I have read his book "Map-Seeking > Circuits in Visual Cognition" and believe that his > approach to computer vision is both powerful and > flexible (although I have an intuition that a Bayesian > version of this sort of system might be a further > improvement). For an introduction to this, look here: > > http://mbi.osu.edu/2002/ws3abstracts.html
Thanks for the link, pretty good web site. His research is very important because we definitely need more theory about cortical processing. I'll check out his book. I'll compare Bayesian learning with the more traditional Hebbian learning. I think Bayesian learning preserves too much information in the probabilities, which increases the computation load, especially with hugh number of nodes. In neural networks there is information loss in each node due to the threshold, in a sense the probabilities are converted to binary values. This makes them more efficient IMO. YKY -- _______________________________________________ Find what you are looking for with the Lycos Yellow Pages http://r.lycos.com/r/yp_emailfooter/http://yellowpages.lycos.com/default.asp?SRC=lycos10 ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
