English   español  
Por favor, use este identificador para citar o enlazar a este item: http://hdl.handle.net/10261/134123
COMPARTIR / IMPACTO:
Estadísticas
logo share SHARE   Add this article to your Mendeley library MendeleyBASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar a otros formatos:
Título

Photonic delay systems as machine learning implementations

AutorHermans, Michiel; Soriano, Miguel C. ; Dambre, Joni; Bienstman, Peter; Fischer, Ingo
Palabras claveOptical computing
Machine learning models
Recurrent neural networks
Fecha de publicación2015
EditorMassachusetts Institute of Technology
CitaciónJournal of Machine Learning Research 16: 2081-2097 (2015)
ResumenNonlinear photonic delay systems present interesting implementation platforms for machine learning models. They can be extremely fast, offer great degrees of parallelism and potentially consume far less power than digital processors. So far they have been successfully employed for signal processing using the Reservoir Computing paradigm. In this paper we show that their range of applicability can be greatly extended if we use gradient descent with backpropagation through time on a model of the system to optimize the input encoding of such systems. We perform physical experiments that demonstrate that the obtained input encodings work well in reality, and we show that optimized systems perform significantly better than the common Reservoir Computing approach. The results presented here demonstrate that common gradient descent techniques from machine learning may well be applicable on physical neuro-inspired analog computers.
URIhttp://hdl.handle.net/10261/134123
Identificadorese-issn: 1533-7928
issn: 1532-4435
Aparece en las colecciones: (IFISC) Artículos
Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
photonic_delay_Hermans.pdf1,05 MBAdobe PDFVista previa
Visualizar/Abrir
Mostrar el registro completo
 


NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.