Minimum Complexity Echo State Network

Rodan, Ali; Tiňo, Peter

doi:10.1109/tnn.2010.2089641

Cited by 594 publications

(427 citation statements)

References 34 publications

Supporting

Mentioning

413

Contrasting

Unclassified

Order By: Relevance

“…It has been shown in [18] that a low complexity structure (which minimizes the number of connections between the neurons) can achieve the same performances as a random interconnection matrix as initially proposed. In the ESN studied in this paper, we used a circular matrix for the connections between the neurons:…”

Section: Echo State Networkmentioning

confidence: 99%

Equalization of the Non-Linear Satellite Communication Channel with an Echo State Network

Bauduin

Smerieri

Massar

et al. 2015

2015 IEEE 81st Vehicular Technology Conference (VTC Spring)

View full text Add to dashboard Cite

Abstract-Because of the small energy available aboard a satellite, the power amplifier must achieve a very high power efficiency which suggest to work close to the saturation point. This would be power efficient, but unfortunately would add non-linear distortions to the communication channel. Several equalization algorithms have been proposed to compensate for this non-linear behaviour. The Echo State Network (ESN), an algorithm coming from the field of artificial neural networks, has also been proposed for this task but has never been compared to state-of-the-art equalizers for non-linear channel. The aim of this paper is to adapt the ESN to the satellite communication channel and to compare it to the baseband Volterra equalizer. We show that the ESN is able to reach the same performances as the Volterra equalizer, evaluated in terms of bit error rate, and has similar complexity. In addition, we propose a new training strategy for the ESN and the Volterra equalizer to improve their performance.

show abstract

Section: Echo State Networkmentioning

confidence: 99%

Equalization of the Non-Linear Satellite Communication Channel with an Echo State Network

Bauduin

Smerieri

Massar

et al. 2015

2015 IEEE 81st Vehicular Technology Conference (VTC Spring)

View full text Add to dashboard Cite

show abstract

“…We experimented with different reservoir sizes, containing between 10 and 50 units. In many ESN applications it has been shown that the reservoir size is an important parameter [19]- [21]. As in all learning systems, there is a tradeoff to reach in that parameter.…”

Section: Methodsmentioning

confidence: 99%

“…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%

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

“…Then, W W T = r 2 I. An example of such a system was studied in detail in [7] under the name Simple Cycle Reservoir (SCR). In SCR the couplings have the cyclic form W = r · [e 2 , e 3 , ..., e N , e 1 ] and 0 < r < 1.…”

Section: Short Term Memory Capacity and Fisher Memory Curve -Symmetric Wmentioning

confidence: 99%

Short term memory in input-driven linear dynamical systems

Tiňo¹,

Rodan²

2013

Neurocomputing

View full text Add to dashboard Cite

We investigate the relation between two quantitative measures characterizing short term memory in input driven dynamical systems, namely the short term memory capacity (MC) [3] and the Fisher memory curve (FMC) [2]. We show that even though MC and FMC map the memory structure of the system under investigation from two quite different perspectives, for linear input driven dynamical systems they are in fact closely related. In particular, under some assumptions, the two quantities can be interpreted as squared 'Mahalanobis' norms of images of the input vector under the system's dynamics. We also offer a detailed rigorous analysis of the relation between MC and FMC in cases of symmetric and cyclic dynamic couplings.

show abstract

Minimum Complexity Echo State Network

Cited by 594 publications

References 34 publications

Equalization of the Non-Linear Satellite Communication Channel with an Echo State Network

Equalization of the Non-Linear Satellite Communication Channel with an Echo State Network

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

Short term memory in input-driven linear dynamical systems

Contact Info

Product

Resources

About