A Unified Framework for Reservoir Computing and Extreme Learning Machines based on a Single Time-delayed Neuron

• Published in: Scientific reports Vol. 5; no. 1; p. 14945
• Main Authors: Ortín, S., Soriano, M. C., Pesquera, L., Brunner, D., San-Martín, D., Fischer, I., Mirasso, C. R., Gutiérrez, J. M.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 08.10.2015; Nature Publishing Group
• Subjects: 631/114/116/2393; 631/114/116/2396; 639/624/1075/401; Computers; Connectivity; Expected values; Feedback; Humanities and Social Sciences; Humans; Information processing; Learning; Machine Learning; multidisciplinary; Neural networks; Neural Networks (Computer); Neurons; Neurons - physiology; Nonlinear Dynamics; Science; Software; User-Computer Interface
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/srep14945

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.