Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Prototypes and matrix relevance learning in complex fourier space

 
: Straat, Michiel; Kaden, Marika; Gay, Matthias; Villmann, Thomas; Lampe, Alexander; Seiffert, Udo; Biehl, Michael; Melchert, Friedrich

:
Postprint urn:nbn:de:0011-n-4737854 (442 KByte PDF)
MD5 Fingerprint: f4e34932a9fc666919b327bb8f47543e
© IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Erstellt am: 31.10.2018


Lamirel, J.-C. ; Institute of Electrical and Electronics Engineers -IEEE-:
12th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization, WSOM+ 2017 : Nancy, France, June 28-30, 2017. Proceedings
Piscataway, NJ: IEEE, 2017
ISBN: 978-1-5090-6638-4 (online)
ISBN: 978-1-5090-6639-1 (print)
S.139-144
International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization (WSOM+) <12, 2017, Nancy>
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IVI ()
Fraunhofer IFF ()

Abstract
In this contribution, we consider the classification of time-series and similar functional data which can be represented in complex Fourier coefficient space. We apply versions of Learning Vector Quantization (LVQ) which are suitable for complex-valued data, based on the so-called Wirtinger calculus. It makes possible the formulation of gradient based update rules in the framework of cost-function based Generalized Matrix Relevance LVQ (GMLVQ). Alternatively, we consider the concatenation of real and imaginary parts of Fourier coefficients in a real-valued feature vector and the classification of time domain representations by means of conventional GMLVQ.

: http://publica.fraunhofer.de/dokumente/N-473785.html