A Unified Framework for Reservoir Computing and Extreme Learning Machines based on a Single Time-delayed Neuron
Open Access
- 8 October 2015
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 5 (1) , 14945
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.Keywords
This publication has 22 references indexed in Scilit:
- Trends in extreme learning machines: A reviewNeural Networks, 2015
- Reservoir computing and extreme learning machines for non-linear time-series data analysisNeural Networks, 2013
- Parallel photonic information processing at gigabyte per second data rates using transient statesNature Communications, 2013
- Optoelectronic Reservoir ComputingScientific Reports, 2012
- Nonlinear System Modeling With Random Matrices: Echo State Networks RevisitedIEEE Transactions on Neural Networks and Learning Systems, 2011
- Information processing using a single dynamical node as complex systemNature Communications, 2011
- Minimum Complexity Echo State NetworkIEEE Transactions on Neural Networks, 2010
- Reservoir computing approaches to recurrent neural network trainingComputer Science Review, 2009
- γ–C plane and robustness in static reservoir for nonlinear regression estimationNeurocomputing, 2009
- Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless CommunicationScience, 2004