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

BICA: a Boolean Independent Component Analysis Algorithm / B. Apolloni, D. Malchiodi, A. Brega - In: HIS 2005 : Fifth International Conference on Hybrid Intelligent Systems : 6-9 November, 2005, Rio de Janeiro, Brasil : proceedings / N. Nedjah [et al.]. - Los Alamitos, CA : IEEE Computer Society, 2005. - ISBN 0769524575. - pp. 131-136 (( Intervento presentato al 5. convegno International Conference on Hybrid Intelligent Systems tenutosi a Rio de Janeiro, Brazil nel 2005.

BICA: a Boolean Independent Component Analysis Algorithm

B. Apolloni
Primo
;
D. Malchiodi
Secondo
;
2005

Abstract

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
Settore INF/01 - Informatica
IEEE Computer Society
IEEE
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
bICA-published.pdf

accesso aperto

Tipologia: Altro
Dimensione 250.96 kB
Formato Adobe PDF
250.96 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/2434/7877
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
social impact