We introduce a procedure for mapping general data records onto Boolean vectors, in the philosophy of ICA procedures. The task is demanded of a neural network with double duty: i) extracting a compressed version of the data in a tight hidden layer of a self-associative multilayer architecture, and ii) mapping it onto Boolean vectors that optimize an entropic target. We prove that the components of these vectors are approximately independent and appreciate their ability to preserve data information in a statistically driven solution of benchmark classification problems.