Hebbian and anti-Hebbian learning for independent component analysis

This paper describes a neural network that self-organizes to recover the original signals from sensor signals. No particular information is required about the statistical properties of the sources and the coefficients of the linear transformation, except the fact that the source signals are statistically independent and nonstationary. The learning rule for the network´s parameters is derived from the steepest descent minimization of a time-dependent cost function that takes the minimum only when the network outputs are uncorrelated with each other