An approach to reservoir computing design and training

Authors:
Aida A. Ferreira;Teresa B. Ludermir;Ronaldo R. B. De Aquino
Affiliations:
Federal University of Pernambuco (UFPE), P.O. Box 7851, Cidade Universitria, Cep: 50.740-530 Recife, PE, Brazil and Federal Institute of Science, Technology and Education of Pernambuco, Av Profess ...;Federal University of Pernambuco (UFPE), P.O. Box 7851, Cidade Universitria, Cep: 50.740-530 Recife, PE, Brazil;Federal University of Pernambuco (UFPE), P.O. Box 7851, Cidade Universitria, Cep: 50.740-530 Recife, PE, Brazil
Venue:
Expert Systems with Applications: An International Journal
Year:
2013

Citing 9
Cited 2

Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence

Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence
Real-time computing without stable states: a new framework for neural computation based on perturbations

Neural Computation
2007 Special Issue: An experimental unification of reservoir computing methods

Neural Networks
2008 Special Issue: Event detection and localization for small mobile robots using reservoir computing

Neural Networks
Using Reservoir Computing for Forecasting Time Series: Brazilian Case Study

HIS '08 Proceedings of the 2008 8th International Conference on Hybrid Intelligent Systems
On the Quantification of Dynamics in Reservoir Computing

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Genetic algorithm for reservoir computing optimization

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
The introduction of time-scales in reservoir computing, applied to isolated digits recognition

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Survey: Reservoir computing approaches to recurrent neural network training

Computer Science Review

Optimization of the weights and asymmetric activation function family of neural network for time series forecasting

Expert Systems with Applications: An International Journal
An automatic method for construction of ensembles to time series prediction

International Journal of Hybrid Intelligent Systems

Quantified Score

Hi-index	12.05

Visualization

Abstract

Reservoir computing is a framework for computation like a recurrent neural network that allows for the black box modeling of dynamical systems. In contrast to other recurrent neural network approaches, reservoir computing does not train the input and internal weights of the network, only the readout is trained. However it is necessary to adjust parameters to create a ''good'' reservoir for a given application. In this study we introduce a method, called RCDESIGN (reservoir computing and design training). RCDESIGN combines an evolutionary algorithm with reservoir computing and simultaneously looks for the best values of parameters, topology and weight matrices without rescaling the reservoir matrix by the spectral radius. The idea of adjust the spectral radius within the unit circle in the complex plane comes from the linear system theory. However, this argument does not necessarily apply to nonlinear systems, which is the case of reservoir computing. The results obtained with the proposed method are compared with results obtained by a genetic algorithm search for global parameters generation of reservoir computing. Four time series were used to validate RCDESIGN.