On Mon, Aug 13, 2012 at 6:47 PM, Steve Richfield <[email protected]>wrote:
> Russell, > > "What we have here is a failure to communicate." > I think so... Not really. If every one of the ~10^10 neurons that have axons and > dendrites connected to 10% of the other neurons (probably close to the > worst possible real case), we have then "only" complicated things by ~7 > orders of magnitude (adjusting downward for present NN complexities). > You're missing the central point. The computational requirement for one iteration may be linear in the number of variables, which with future hardware should end up being tractable even for something as complex as the human brain, as you say. But the size of the search space is *exponential* in the number of variables. If you have ten thousand variables (equivalent to some simple invertebrate brains), you're looking at computational effort, not of 10^4 operations, but exp(10^4). That's the problem. ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-c97d2393 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968 Powered by Listbox: http://www.listbox.com
