PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

BICA: a Boolean independent component analysis algorithm
Bruno Apolloni, Andrea Brega and Dario Malchiodi
In: HIS 2005, 6-9 Nov 2005, Rio de Janeiro, Brasil.


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.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:1332
Deposited By:Dario Malchiodi
Deposited On:28 November 2005