STORAGE OF CORRELATED PATTERNS IN A PERCEPTRON

We calculate the storage capacity of a perceptron for correlated Gauss ian patterns. We find that the storage capacity alpha(c) can be less t han 2 if similar patterns are mapped onto different outputs and vice v ersa. As long as the patterns are in a general position we obtain, in contrast to previous works, that alpha(c) greater than or equal to 1 i n agreement with Cover's theorem. Numerical simulations confirm the re sults.