Competing neural networks: Finding a strategy for the game of matching pennies

The ability of a deterministic, plastic system to learn to imitate stochast ic behavior is analyzed. Two neural networks-actually, two perceptrons-are put to play a zero-sum game one against the other. The competition, by acti ng as a kind of mutually supervised learning, drives the networks to produc e an. approximation to the optimal strategy, that is to say, a random signa l.