Dear John, thanks for the explanations (and paper announcement).
>> ... (1 + delta)^(m*n). > > This is true, and a delta > 2 follows from a Theorem in an > upcoming paper by Matthieu Walraet and myself. Do you mean (1+delta) > 2, or really (1+delta) > 3? > > Might neural nets help to find (very) long games > > for given board size? > > Neural nets are not the best way to deal with avoiding superko:-( I had some special way to use them in mind - but too complicated to explain it here. Please let us know when a preprint is available on ArXiv or some other place. Cheers, Ingo. PS. I am just a guest of Richard Lorentz in LA. He met you only once (back in Summer 2002 in Maastricht). Richard still remembers vividly your research energy! Keep it alive. _______________________________________________ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go