Digital hardware architectures of Kohonen's self organizing feature maps with exponential neighboring function

Jorge Peña, Mauricio Vanegas, Andrés Valencia

Producción científica: Capítulo del libro/informe/acta de congresoPonencia publicada en las memorias del evento con ISBNrevisión exhaustiva

23 Citas (Scopus)

Resumen

Kohonen maps are self-organizing neural networks that categorize input data, capturing its topology and probability distribution. Efficient hardware implementations of such maps require the definition of a certain number of simplifications to the original algorithm. In particular, multiplications have to be avoided by means of choices in the distance metric, the neighborhood function and the set of learning parameter values. In this paper, one-dimensional and bi-dimensional Kohonen maps with exponential neighboring function and Cityblock and Chessboard norms are defined, and their hardware architecture is presented. VHDL simulations and synthesis on an FPGA of the proposed architectures demonstrate both satisfactory functionality and feasibility.

Idioma originalInglés
Título de la publicación alojadaProceedings of the 2006 IEEE International Conference on Reconfigurable Computing and FPGA's, ReConFig 2006
Páginas114-121
Número de páginas8
DOI
EstadoPublicada - 2006
Evento2006 IEEE International Conference on Reconfigurable Computing and FPGA's, ReConFig 2006 - San Luis Potosi, México
Duración: 20 sep. 200622 sep. 2006

Serie de la publicación

NombreProceedings of the 2006 IEEE International Conference on Reconfigurable Computing and FPGA's, ReConFig 2006

Conferencia

Conferencia2006 IEEE International Conference on Reconfigurable Computing and FPGA's, ReConFig 2006
País/TerritorioMéxico
CiudadSan Luis Potosi
Período20/09/0622/09/06

Huella

Profundice en los temas de investigación de 'Digital hardware architectures of Kohonen's self organizing feature maps with exponential neighboring function'. En conjunto forman una huella única.

Citar esto