Reservoir Computing Approaches for Representation and Classification of Multivariate Time Series

Bianchi, Filippo Maria; Scardapane, Simone; Løkse, Sigurd; Jenssen, Robert

doi:10.1109/tnnls.2020.3001377

Cited by 136 publications

(86 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Training of A80%B20%C showed comparable results. An Echo State Network for multivariate time series classification [29] with reservoir size N = 45, 25% connectivity and leakage 60% was used for classification of movement primitives. Movement patterns were identified as not classified below a 55% threshold.…”

Section: Preparatory Analysis Of Training Resultsmentioning

confidence: 99%

Leading or Following? Dyadic Robot Imitative Interaction Using the Active Inference Framework

Wirkuttis

Tani

2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Section: Preparatory Analysis Of Training Resultsmentioning

confidence: 99%

Leading or Following? Dyadic Robot Imitative Interaction Using the Active Inference Framework

Wirkuttis

Tani

2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

“…In particular, in [ 43 ] the authors showed that ESNs presented maximal information storage and transfer, as well as enhanced memory capacity right at the edge of chaos. However, while ESNs and other RC approaches have been previously applied to classification tasks with very good results [ 31 , 49 , 50 , 51 , 52 , 53 ], to the best of our knowledge, an analysis of the influence of the dynamical regime on the performance of RC architectures for classification tasks is still missing.…”

Section: Resultsmentioning

confidence: 99%

“…Several readout methods have been proposed in the literature to transform the information contained in the reservoir dynamics into the expected target output

, ranging from linear regressions methods over the reservoir states [ 28 , 29 ], to the use of “support vector machines” or “multilayer perceptrons as decoders [ 30 ]”. Here, we use a simple Ridge regression (see Appendix A for a detailed explanation of the algorithm) over the “reservoir model space” , a method that has been recently proposed for the classification of multivariate time series [ 31 ].…”

Section: Methodsmentioning

confidence: 99%

Optimal Input Representation in Neural Systems at the Edge of Chaos

Morales¹,

Muñoz²

2021

Biology

View full text Add to dashboard Cite

Shedding light on how biological systems represent, process and store information in noisy environments is a key and challenging goal. A stimulating, though controversial, hypothesis poses that operating in dynamical regimes near the edge of a phase transition, i.e., at criticality or the “edge of chaos”, can provide information-processing living systems with important operational advantages, creating, e.g., an optimal trade-off between robustness and flexibility. Here, we elaborate on a recent theoretical result, which establishes that the spectrum of covariance matrices of neural networks representing complex inputs in a robust way needs to decay as a power-law of the rank, with an exponent close to unity, a result that has been indeed experimentally verified in neurons of the mouse visual cortex. Aimed at understanding and mimicking these results, we construct an artificial neural network and train it to classify images. We find that the best performance in such a task is obtained when the network operates near the critical point, at which the eigenspectrum of the covariance matrix follows the very same statistics as actual neurons do. Thus, we conclude that operating near criticality can also have—besides the usually alleged virtues—the advantage of allowing for flexible, robust and efficient input representations.

show abstract

“…A large variety of time series dissimilarity measures have been proposed in the literature, including those based on statistical methods [4], signal processing [5], kernel methods [6], and reservoir computing [7]. In this paper, we adopt the Dynamic Time Warping (DTW) distance [8], which is an efficient and well-known algorithm that computes the dissimilarity between two sequences as the cost required to obtain an optimal match between them.…”

Section: Cluster Analysis Of R(t)-curvesmentioning

confidence: 99%

Intervention Fatigue is the Primary Cause of Strong Secondary Waves in the COVID-19 Pandemic

Rypdal

Bianchi

Rypdal

2020

IJERPH

Self Cite

View full text Add to dashboard Cite

As of November 2020, the number of COVID-19 cases was increasing rapidly in many countries. In Europe, the virus spread slowed considerably in the late spring due to strict lockdown, but a second wave of the pandemic grew throughout the fall. In this study, we first reconstruct the time evolution of the effective reproduction numbers R(t) for each country by integrating the equations of the classic Susceptible-Infectious-Recovered (SIR) model. We cluster countries based on the estimated R(t) through a suitable time series dissimilarity. The clustering result suggests that simple dynamical mechanisms determine how countries respond to changes in COVID-19 case counts. Inspired by these results, we extend the simple SIR model for disease spread to include a social response to explain the number X(t) of new confirmed daily cases. In particular, we characterize the social response with a first-order model that depends on three parameters ν1,ν2,ν3. The parameter ν1 describes the effect of relaxed intervention when the incidence rate is low; ν2 models the impact of interventions when incidence rate is high; ν3 represents the fatigue, i.e., the weakening of interventions as time passes. The proposed model reproduces typical evolving patterns of COVID-19 epidemic waves observed in many countries. Estimating the parameters ν1,ν2,ν3 and initial conditions, such as R0, for different countries helps to identify important dynamics in their social responses. One conclusion is that the leading cause of the strong second wave in Europe in the fall of 2020 was not the relaxation of interventions during the summer, but rather the failure to enforce interventions in the fall.

show abstract

Reservoir Computing Approaches for Representation and Classification of Multivariate Time Series

Cited by 136 publications

References 47 publications

Leading or Following? Dyadic Robot Imitative Interaction Using the Active Inference Framework

Leading or Following? Dyadic Robot Imitative Interaction Using the Active Inference Framework

Optimal Input Representation in Neural Systems at the Edge of Chaos

Intervention Fatigue is the Primary Cause of Strong Secondary Waves in the COVID-19 Pandemic

Contact Info

Product

Resources

About