FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting

Hardware implementation of artificial neural networks (ANNs) allows exploiting the inherent parallelism of these systems. Nevertheless, they require a large amount of resources in terms of area and power dissipation. Recently, Reservoir Computing (RC) has arisen as a strategic technique to design re...

Full description

Bibliographic Details
Main Authors:	Miquel L. Alomar, Vincent Canals, Nicolas Perez-Mora, Víctor Martínez-Moll, Josep L. Rosselló
Format:	Article
Language:	English
Published:	Hindawi Limited 2016-01-01
Series:	Computational Intelligence and Neuroscience
Online Access:	http://dx.doi.org/10.1155/2016/3917892

id	doaj-4c3cab460880454db82dc8b2d06c6cf9
record_format	Article
spelling	doaj-4c3cab460880454db82dc8b2d06c6cf92020-11-24T23:07:37ZengHindawi LimitedComputational Intelligence and Neuroscience1687-52651687-52732016-01-01201610.1155/2016/39178923917892FPGA-Based Stochastic Echo State Networks for Time-Series ForecastingMiquel L. Alomar0Vincent Canals1Nicolas Perez-Mora2Víctor Martínez-Moll3Josep L. Rosselló4Physics Department, University of the Balearic Islands, 07122 Palma de Mallorca, SpainPhysics Department, University of the Balearic Islands, 07122 Palma de Mallorca, SpainPhysics Department, University of the Balearic Islands, 07122 Palma de Mallorca, SpainPhysics Department, University of the Balearic Islands, 07122 Palma de Mallorca, SpainPhysics Department, University of the Balearic Islands, 07122 Palma de Mallorca, SpainHardware implementation of artificial neural networks (ANNs) allows exploiting the inherent parallelism of these systems. Nevertheless, they require a large amount of resources in terms of area and power dissipation. Recently, Reservoir Computing (RC) has arisen as a strategic technique to design recurrent neural networks (RNNs) with simple learning capabilities. In this work, we show a new approach to implement RC systems with digital gates. The proposed method is based on the use of probabilistic computing concepts to reduce the hardware required to implement different arithmetic operations. The result is the development of a highly functional system with low hardware resources. The presented methodology is applied to chaotic time-series forecasting.http://dx.doi.org/10.1155/2016/3917892
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Miquel L. Alomar Vincent Canals Nicolas Perez-Mora Víctor Martínez-Moll Josep L. Rosselló
spellingShingle	Miquel L. Alomar Vincent Canals Nicolas Perez-Mora Víctor Martínez-Moll Josep L. Rosselló FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting Computational Intelligence and Neuroscience
author_facet	Miquel L. Alomar Vincent Canals Nicolas Perez-Mora Víctor Martínez-Moll Josep L. Rosselló
author_sort	Miquel L. Alomar
title	FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting
title_short	FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting
title_full	FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting
title_fullStr	FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting
title_full_unstemmed	FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting
title_sort	fpga-based stochastic echo state networks for time-series forecasting
publisher	Hindawi Limited
series	Computational Intelligence and Neuroscience
issn	1687-5265 1687-5273
publishDate	2016-01-01
description	Hardware implementation of artificial neural networks (ANNs) allows exploiting the inherent parallelism of these systems. Nevertheless, they require a large amount of resources in terms of area and power dissipation. Recently, Reservoir Computing (RC) has arisen as a strategic technique to design recurrent neural networks (RNNs) with simple learning capabilities. In this work, we show a new approach to implement RC systems with digital gates. The proposed method is based on the use of probabilistic computing concepts to reduce the hardware required to implement different arithmetic operations. The result is the development of a highly functional system with low hardware resources. The presented methodology is applied to chaotic time-series forecasting.
url	http://dx.doi.org/10.1155/2016/3917892
work_keys_str_mv	AT miquellalomar fpgabasedstochasticechostatenetworksfortimeseriesforecasting AT vincentcanals fpgabasedstochasticechostatenetworksfortimeseriesforecasting AT nicolasperezmora fpgabasedstochasticechostatenetworksfortimeseriesforecasting AT victormartinezmoll fpgabasedstochasticechostatenetworksfortimeseriesforecasting AT joseplrossello fpgabasedstochasticechostatenetworksfortimeseriesforecasting
_version_	1725618016730742784

FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting

Similar Items