The Art of Doing Science and Engineering: Learning to Learn

by Richard Hamming

then slightly altered one (or more) of these parameters. Then he made one formula play, say, ten games against the other, and the formula which won the most games was clearly (actually only probably) the better program. The machine went on perturbing the same parameters until it came to a local optimum, whereupon it shifted to other parameters. Thus it went around and around, repeatedly using the same parameters, gradually emerging with a significantly better checkers-playing program—certainly much better than was Samuel himself. The program even beat a Connecticut state checkers champion! Is it not fair to say, “The program