A Unified Framework for Reservoir Computing and Extreme Learning Machines based on a Single Time-delayed Neuron.
S Ortín, M C Soriano, L Pesquera, D Brunner, D San-Martín, I Fischer, C R Mirasso, J M Gutiérrez
Author Information
S Ortín: Instituto de Física de Cantabria, CSIC-Universidad de Cantabria, E-39005 Santander, Spain.
M C Soriano: Instituto de Física Interdisciplinar y Sistemas Complejos, IFISC (CSIC-UIB), Campus Universitat Illes Balears, E-07122 Palma de Mallorca, Spain.
L Pesquera: Instituto de Física de Cantabria, CSIC-Universidad de Cantabria, E-39005 Santander, Spain.
D Brunner: Instituto de Física Interdisciplinar y Sistemas Complejos, IFISC (CSIC-UIB), Campus Universitat Illes Balears, E-07122 Palma de Mallorca, Spain.
D San-Martín: Predictia Intelligent Data Solutions S.L., E-39011 Santander, Spain.
I Fischer: Instituto de Física Interdisciplinar y Sistemas Complejos, IFISC (CSIC-UIB), Campus Universitat Illes Balears, E-07122 Palma de Mallorca, Spain.
C R Mirasso: Instituto de Física Interdisciplinar y Sistemas Complejos, IFISC (CSIC-UIB), Campus Universitat Illes Balears, E-07122 Palma de Mallorca, Spain.
J M Gutiérrez: Instituto de Física de Cantabria, CSIC-Universidad de Cantabria, E-39005 Santander, Spain.
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.
