Date: 2005-04-07 12:49 pm (UTC)
mair_in_grenderich: (Default)
well, you can wrap the various components in non-linear functions, approximate the whole thing by a neural network, I still say that you're looking for equality in the final computations of the "badness" of the two actions.

I guess what I'm saying, is that it seems to me that what I think the "right" thing to do may be clear, but I might not want to do it anyway.
If you don't have an account you can create one now.
HTML doesn't work in the subject.
More info about formatting

If you are unable to use this captcha for any reason, please contact us by email at support@dreamwidth.org