Re: Turing test

[Sidney R Maxwell III <smaxwell@xxxxxxxxxxxxx>]

>On May 29,  8:31am, keith reid-green wrote:
> Subject: [CM>] CM> Checkers
> In the 1950s somebody (at IBM?) wrote a checkers program that was
> self-learning.  He programmed the computer's moves only to follow the rules
> of checkers--no intelligence in the computer program, except that when the
> machine lost a game, it retained all the board positions for that game and
> tried not to replicate any of them in subsequent games.  The author claimed
> that after about 15 games the computer won one, lost the next two and was
> unbeatable thereafter.
>
> I would like to read a primary source description of this early machine
> intelligence experiment.  Can anybody cite the source material, or better
> yet, send me a copy?

The somebody as Arthur Samuels, who later went to Stanford University's
Artificial Intellegence Laboratory.  I don't believe that his reported
results were quite as stellar as you suggest, in that it took more time, but
the ultimate result is that his program is consider to be the best checker
player in the world.

-+- Sid Maxwell

Samuel, A. L., 1959, "Some Studies in Machine Learning Using the Game of
Checkers", IBM Journal of Research and Development, Vol 3, No 3, pp 210-229.
Also in "Computers and Thought", E. Feignbaum and J. Feldman (eds.), New
York: McGraw-Hill Book Company, 1963.

Samuel, A. L., 1960, "Programming a Computer to Play Games", Advances in
Computers, Vol 1, F. Alt (ed), New Yourk: Academic Press, 1960, pp 165-192.

Samuel, A. L., 1967, "Some Studies in Machine Learning Using the Game of
Checkers, II - Recent Progress", IBM Journal of Research and Development,
Nov 1967, pp 601-617.