A Unified Framework for Reservoir Computing and Extreme Learning Machines based on a Single Time-delayed Neuron
Ortín, Silvia; Soriano, Miguel C.; Pesquera, Luis; Brunner, Daniel; San-Martín, Daniel; Fischer, Ingo; Mirasso, Claudio R.; Gutiérrez, José Manuel
Scientific Reports 5, 14945 (2015)
Scientific Reports 5, 14945 (2015)
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.
Related research projects
INTENSE@COSYP
COMPLEX SYSTEMS PHYSICS: INFORMATION, TECHNOLOGY, SOCIETY AND ECOLOGY
P.I.: Maxi San Miguel
-
TRIPHOP
Towards brain-inspired efficient photonic information processing
P.I.: Ingo Fischer
Information processing is a major challenge in our information-driven society, and the demand will grow further in the future. Large amounts of data need to be processed in communication networks, but also …
GrupCompetitiu-
Grup Competitiu FESC
P.I.: Ingo Fischer
Grupo muy competitivo de Fisica Experimental de Sistemas Complejos