AMSOM : artificial metaplasticity in SOM neural networks: Application to MIT-BIH arrhythmias database

Torres Alegre, Santiago ORCID: https://orcid.org/0000-0002-9945-105X, Fombellida Vetas, Juan, Piñuela Izquierdo, Juan Antonio and Andina de la Fuente, Diego ORCID: https://orcid.org/0000-0001-7036-2646 (2018). AMSOM : artificial metaplasticity in SOM neural networks: Application to MIT-BIH arrhythmias database. "Neural Computing and Applications", v. 30 (n. 1); pp. 1-8. ISSN 0941-0643. https://doi.org/10.1007/s00521-018-3576-0.

Descripción

Título: AMSOM : artificial metaplasticity in SOM neural networks: Application to MIT-BIH arrhythmias database
Autor/es:
Tipo de Documento: Artículo
Título de Revista/Publicación: Neural Computing and Applications
Fecha: Julio 2018
ISSN: 0941-0643
Volumen: 30
Número: 1
Materias:
ODS:
Palabras Clave Informales: Metaplasticity, AMMLP, AMP, Feature extraction, Artificial neural network, Self-organizing maps, AMSOM
Escuela: E.T.S.I. Telecomunicación (UPM)
Departamento: Señales, Sistemas y Radiocomunicaciones
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[thumbnail of INVE_MEM_2018_299542.pdf]
Vista Previa
PDF (Portable Document Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (1MB) | Vista Previa

Resumen

Artificial metaplasticity is the machine learning algorithm inspired in the biological metaplasticity of neural synapses. Metaplasticity stands for plasticity of plasticity, and as long as plasticity is related to memory, metaplasticity is related to learning. Implemented in supervised learning assuming input patterns distribution or a related function, it has proved to be very efficient in performance and in training convergence for multidisciplinary applications. Now, for the first time, this kind of artificial metaplasticity is implemented in an unsupervised neural network, achieving also excellent results that are presented in this paper. To compare results, a modified self-organization map is applied to the classification of MIT-BIH cardiac arrhythmias database.

Más información

ID de Registro: 54999
Identificador DC: https://oa.upm.es/54999/
Identificador OAI: oai:oa.upm.es:54999
URL Portal Científico: https://portalcientifico.upm.es/es/ipublic/item/5654086
Identificador DOI: 10.1007/s00521-018-3576-0
URL Oficial: https://www.springerprofessional.de/amsom-artifici...
Depositado por: Memoria Investigacion
Depositado el: 28 May 2019 15:39
Ultima Modificación: 12 Nov 2025 00:00