Texto completo
Vista Previa |
PDF (Portable Document Format)
- Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (520kB) | Vista Previa |
On the Biological Plausibility of Artificial Metaplasticity
Cita
Andina de la Fuente, Diego 
ORCID: https://orcid.org/0000-0001-7036-2646
(2011).
On the Biological Plausibility of Artificial Metaplasticity.
En: "4th International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2011", 30/05/2011 - 03/06/2011, La Palma, Islas Canarias, España. ISBN 978-3-642-21343-4. pp. 119-128.
https://doi.org/10.1007/978-3-642-21344-1_13.
ORCID: https://orcid.org/0000-0001-7036-2646
(2011).
On the Biological Plausibility of Artificial Metaplasticity.
En: "4th International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2011", 30/05/2011 - 03/06/2011, La Palma, Islas Canarias, España. ISBN 978-3-642-21343-4. pp. 119-128.
https://doi.org/10.1007/978-3-642-21344-1_13.
Descripción
| Título: | On the Biological Plausibility of Artificial Metaplasticity |
|---|---|
| Autor/es: |
|
| Tipo de Documento: | Ponencia en Congreso o Jornada (Sin especificar) |
| Título del Evento: | 4th International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2011 |
| Fechas del Evento: | 30/05/2011 - 03/06/2011 |
| Lugar del Evento: | La Palma, Islas Canarias, España |
| Título del Libro: | Proceedings of 4th International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2011 |
| Fecha: | 2011 |
| ISBN: | 978-3-642-21343-4 |
| Materias: | |
| ODS: | |
| Escuela: | E.T.S.I. Telecomunicación (UPM) |
| Departamento: | Señales, Sistemas y Radiocomunicaciones |
| Licencias Creative Commons: | Reconocimiento - Sin obra derivada - No comercial |
Resumen
The training algorithm studied in this paper is inspired by the biological metaplasticity property of neurons. Tested on different multidisciplinary applications, it achieves a more efficient training and improves Artificial Neural Network Performance. The algorithm has been recently proposed for Artificial Neural Networks in general, although for the purpose of discussing its biological plausibility, a Multilayer Perceptron has been used. During the training phase, the artificial metaplasticity multilayer perceptron could be considered a new probabilistic version of the presynaptic rule, as during the training phase the algorithm assigns higher values for updating the weights in the less probable activations than in the ones with higher probability
Más información
| ID de Registro: | 13268 |
|---|---|
| Identificador DC: | https://oa.upm.es/13268/ |
| Identificador OAI: | oai:oa.upm.es:13268 |
| Identificador DOI: | 10.1007/978-3-642-21344-1_13 |
| URL Oficial: | http://link.springer.com/chapter/10.1007/978-3-642... |
| Depositado por: | Memoria Investigacion |
| Depositado el: | 28 Nov 2012 10:38 |
| Ultima Modificación: | 26 Sep 2014 17:01 |
Acciones
- Estadísticas
- Exportar cita
- Editar (sólo personal del Archivo)
