Foundations of Immunocomputing

Author

Tarakanov, Alexander ; Nicosia, Giuseppe

Author_Institution

St. Petersburg Inst. for Informatics & Autom., Russian Acad. of Sci., St. Petersburg

fYear

2007

fDate

1-5 April 2007

Firstpage

503

Lastpage

508

Abstract

This paper presents the mathematical basis of the immunocomputing using feature extraction and pattern recognition. The key notions of the approach are the formal immune network (FIN) and the coding theory for machine learning. The training of FIN includes apoptosis (programmed cell death) and auto immunization both controlled by cytokines (messenger proteins), whereas parameters of FIN can be optimized by Kullback entropy. Recent results suggest that the approach outperforms (by training time and accuracy) state-of-art approaches of computational intelligence

Keywords

artificial immune systems; learning (artificial intelligence); pattern recognition; Kullback entropy; autoimmunization; coding theory; feature extraction; formal immune network; immunocomputing; machine learning; messenger proteins; pattern recognition; programmed cell death; Application specific integrated circuits; Artificial neural networks; Biology computing; Biomedical signal processing; Computational intelligence; Computer networks; Feature extraction; Immune system; Pattern recognition; Proteins;

fLanguage

English

Publisher

ieee

Conference_Titel

Foundations of Computational Intelligence, 2007. FOCI 2007. IEEE Symposium on

Conference_Location

Honolulu, HI

Print_ISBN

1-4244-0703-6

Type

conf

DOI

10.1109/FOCI.2007.371519

Filename

4233953