From: Matt Mahoney (matmahoney@yahoo.com)
Date: Wed Nov 26 2008 - 14:34:20 MST
--- On Wed, 11/26/08, Vladimir Nesov <robotact@gmail.com> wrote:
> Heh. But you are only considering complexity of a counter, t, your
> O(log t) related to the fact that many counter values are not
> compressible. It has nothing to do with prior information about
> environment, in fact there is no communication with environment in
> your model. You also don't reflect the work on optimization of
> intelligence, as you could run t^t^t^t steps instead of t steps for
> given value of t and have the same result. There is no utility in
> complexity, if said complexity is noise.
I make no claim about the impossibility of self improvement with respect to speed optimization. In fact, I give a counterexample in my paper.
-- Matt Mahoney, matmahoney@yahoo.com
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:03 MDT