Re: [computer-go] SlugGo vs Many Faces, newest data

[Don Dailey <drd@xxxxxxx>]

>    You have ruled out most of my ideas for why you could say
>    'So if I do something to my program and it tests 9-1, for instance, I just 
>    laugh.'  If you haven't
>    succeeded in improving your code, then the probability of it testing 9-1 or 
>    10-0 is at most 11/1024, which is about 1/93.  Of course this does not say 
>    that with these results, the probability that you have improved the 
>    programme is 92/93, but to laugh at such a result, I would think you would 
>    estimate a prior of maybe only a 1/200 chance of improvement.  Could this 
>    be the explanation?  Is my psychological ability letting me down when I 
>    interpret your laughter?  Maybe I am misinterpreting something here.

What I'm trying  to say isn't as deep as you  probably think.  All I'm
saying is that I DO have a bias based on prior expectations.  I rarely
make a  program change that  I think will  improve my program  by more
than  a few percentage  points, so  if I  get a  9-1 start,  I "laugh"
knowing that I will be happy with  a 55% result.  Of course I start to
reset  my expectations  and wonder  if the  change was  better  than I
expected, but I  still realize that I'm not going  to continue to test
at 90%

 
EXAMPLE:

If you threw a coin 10 times  and got 9 heads, you would also laugh in
the sense  that you probably would  not report that you  found a trick
coin that  returns heads 90%  of the time.   Despite a 9-1  heads over
tails victory, your common sense (and prior expectations) will prevail
and you will  continue to believe the coin is more  or less fair.  You
will more  than likely  assume that if  you keep throwing,  the result
will gradually approach 0.50.    And you would probably be right.

- Don
_______________________________________________
computer-go mailing list
computer-go@xxxxxxxxxxxxxxxxx
http://www.computer-go.org/mailman/listinfo/computer-go/