A Unified Framework for Reservoir Computing and Extreme Learning Machines based on a Single Time-delayed Neuron
View/ Open
Full record
Show full item recordAuthor
Ortín González, Silvia; Soriano, Miguel C.; Pesquera González, Luis
Date
2015-10-08Derechos
Atribución 4.0 Internacional
Publicado en
Scientific Reports 5, Article number: 14945 (2015)
Publisher
Macmillan
Enlace a la publicación
Palabras clave
Dynamical systems
Learning algorithms
Optoelectronic devices and components
Abstract:
In this paper we present a unified framework for extreme learning machines and reservoir computing (echo state networks), which can be physically implemented using a single nonlinear neuron subject to delayed feedback. The reservoir is built within the delay-line, employing a number of “virtual” neurons. These virtual neurons receive random projections from the input layer containing the information to be processed. One key advantage of this approach is that it can be implemented efficiently in hardware. We show that the reservoir computing implementation, in this case optoelectronic, is also capable to realize extreme learning machines, demonstrating the unified framework for both schemes in software as well as in hardware.
Collections to which it belong
- D52 Artículos [505]