Optimization and applications of echo state networks with leaky- integrator neurons

Jaeger, Herbert; Lukoševičius, Mantas; Popovici, Dan; Siewert, Udo

doi:10.1016/j.neunet.2007.04.016

Cited by 759 publications

(477 citation statements)

References 17 publications

Supporting

Mentioning

471

Contrasting

Unclassified

Order By: Relevance

“…Even though spiking neurons have more computational power than sigmoidal neurons [18], we have chosen to use the ESN for estimating PESQ scores in real-time. In the past few years there has been a growing interest in the ESN model, since it has been proven efficient and robust in many machine learning benchmark problems [4], [5], [7]- [9], [19]- [21]. The device proposed in this paper is based on this tool, in order to exploit its simplicity and its robustness.…”

Section: Description Of the Methods Proposedmentioning

confidence: 99%

“…The initial states of the neurons are basically arbitrarily chosen (for details, see [4], [5]). It is better to see this system as a dynamical one when it is in operation.…”

Section: Description Of the Methods Proposedmentioning

confidence: 99%

“…The latter are, in general, very powerful to learn non-linear mappings (which is the case in assessing perceptual quality) using sequential training algorithms. However, their use has been limited mainly due to the inefficiency of their learning algorithms [4], [5], which suffer from slow convergence rates and low robustness, thus in particular limiting their applicability in real-time contexts.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Real-Time Estimation of Speech Quality through the Internet Using Echo State Networks

Basterrech¹,

Rubino²

2013

JACN

View full text Add to dashboard Cite

Abstract-Audio quality in the Internet can be strongly affected by network conditions. As a consequence, many techniques to evaluate it have been developed. In particular, the ITU-T adopted in 2001 a technique called Perceptual Evaluation of Speech Quality (PESQ) to automatically measuring speech quality. PESQ is a well-known and widely used procedure, providing in general an accurate evaluation of perceptual quality by comparing the original and received voice sequences.One obvious inherent limitation of PESQ is, thus, that it requires the original signal (we say the reference), to make its evaluation. This precludes the use of PESQ for assessing the perceived quality in real-time, as the reference is in general not available.In this paper, we describe a procedure for estimating PESQ output working only with measures taken on the network state and properties of the communication system, without any use of the reference. It is based on the use of statistical learning techniques. Specifically, we rely on recent ideas for learning with specific types of neural networks, known under the name of Echo State Networks (ESNs), a member of the class of Reservoir Computing systems. These tools have been proven to be very efficient and robust in many learning tasks. The experimental results obtained show the good accuracy of the resulting procedure, and its capability to give its estimations of speech quality in a real-time context. This allows putting our measuring modules in future Internet applications or services based on voice transmission, for instance for control purposes.Index Terms-Quality assessment, speech quality, echo state networks, reservoir computing. I. INTRODUCTIONMeasuring the quality of a voice signal transmitted over the Internet is an important topic today, and one of main available tools for this purpose is the Perceptual Evaluation of Speech Quality (PESQ) method accepted in 2001 as the ITU-T objective speech quality measurement standard P.862 [1]. The network conditions vary over time, and in many contexts, several different factors lead to losses, which in turn lead to degradations in the perception of the quality by the users. PESQ analyzes this quality by comparing the received signal with the original speech sequence. For this reason, we say that it is a "full reference" technique, the reference being the original signal. Researchers in many areas use PESQ and the tool has been widely diffused in commercial measurement products. Recently, the ITU started to update its voice Manuscript received March 1, 2013; revised April 15, 2013. This work was supported in part by the European Celtic Project "QuEEN".S. Basterrech is with the University of Rennes 2, Rennes, France (e-mail: Sebastian.Basterrechtiscordio@etudiant.uhb.fr).G. Rubino is with the National Institute for Research in Computer Science and Control (INRIA Rennes -Bretagne Atlantique), Rennes, France (e-mail: Gerardo.Rubino@inria.fr). assessment recommendations by promoting the new P.863 standard Perceptual Objective Listening Quality Asse...

show abstract

Section: Description Of the Methods Proposedmentioning

confidence: 99%

“…The initial states of the neurons are basically arbitrarily chosen (for details, see [4], [5]). It is better to see this system as a dynamical one when it is in operation.…”

Section: Description Of the Methods Proposedmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Estimation of Speech Quality through the Internet Using Echo State Networks

Basterrech¹,

Rubino²

2013

JACN

View full text Add to dashboard Cite

show abstract

“…Importantly, these parameters are both interdependent and dependent on the problem at hand. For instance, the leakage rate and spectral radius will affect both each other and the memory length of the network [21].…”

Section: ) Autoregressive Model: An Autoregressive Model (Ar)mentioning

confidence: 99%

Effects of data cleansing on load prediction algorithms

Høverstad

Tidemann

Langseth

2013

2013 IEEE Computational Intelligence Applications in Smart Grid (CIASG)

View full text Add to dashboard Cite

Abstract-The rollout of advanced metering infrastructure that is planned in many countries worldwide will lead to a massive inflow of data from moderately reliable sensory equipment. In principle, this will make intelligent and automated planning and operation possible at an increasingly finer scale in the electric grid. However, errors can creep into the meter data, either from faulty sensors or during transmission from the meters to the database. This work studies the role of data cleansing as a preprocessing step for short-term (24-hour) power load prediction. We focus on cleansing and prediction at several levels of granularity, from the transmission level via distribution substations down to single households.We believe that preprocessing filters such as cleansing should lead to more robustness and/or precision in the subsequent processing step. However, load cleansing frameworks tend to make the popular assumption of normally and independently distributed noise in the time series. We show that this is incorrect at the diurnal level, due to the characteristic pattern of power consumption, with two peak loads during daytime and a nighttime trough. Moreover, we present empirical evidence that a preprocessing step based on this assumption fails to contribute positively to the performance of the subsequent prediction step. To rectify this problem, we suggest to subtract the average power load consumption in a given period before cleansing. We present empirical evidence that this improves the robustness and efficiency of load cleansing as a preprocessing step. Data cleansing and load prediction is performed by a system that searches out parameters using an evolutionary approach.

show abstract

“…Genetic Programming (GP) [34], a special class of genetic algorithm (GA), is used to model the optimum gait generation for a quadruped robot [35], and to establish an error correction (calibration) model of ill-conditioned inverse kinematics for a robot [36]. An Echo State Network (ESN) is used for nonlinear dynamical modeling [37], and modeling the localization capability and the navigation skill for a mobile robot. [38].…”

Section: Machine Learning Techniques For Modeling Robotic Tasksmentioning

confidence: 99%

Estimating the non-linear dynamics of free-flying objects

Kim

Billard

2012

Robotics and Autonomous Systems

View full text Add to dashboard Cite

a b s t r a c tThis paper develops a model-free method to estimate the dynamics of free-flying objects. We take a realistic perspective to the problem and investigate tracking accurately and very rapidly the trajectory and orientation of an object so as to catch it in flight. We consider the dynamics of complex objects where the grasping point is not located at the center of mass.To achieve this, a density estimate of the translational and rotational velocity is built based on the trajectories of various examples. We contrast the performance of six non-linear regression methods (Support Vector Regression (SVR) with Radial Basis Function (RBF) kernel, SVR with polynomial kernel, Gaussian Mixture Regression (GMR), Echo State Network (ESN), Genetic Programming (GP) and Locally Weighted Projection Regression (LWPR)) in terms of precision of recall, computational cost and sensitivity to choice of hyper-parameters. We validate the approach for real-time motion tracking of 5 daily life objects with complex dynamics (a ball, a fully-filled bottle, a half-filled bottle, a hammer and a pingpong racket). To enable real-time tracking, the estimated model of the object's dynamics is coupled with an Extended Kalman Filter for robustness against noisy sensing.

show abstract

Optimization and applications of echo state networks with leaky- integrator neurons

Cited by 759 publications

References 17 publications

Real-Time Estimation of Speech Quality through the Internet Using Echo State Networks

Real-Time Estimation of Speech Quality through the Internet Using Echo State Networks

Effects of data cleansing on load prediction algorithms

Estimating the non-linear dynamics of free-flying objects

Contact Info

Product

Resources

About