Computing with transiently stable states

Ozturk, M.C.; Prı́ncipe, José C.

doi:10.1109/ijcnn.2005.1556092

Cited by 16 publications

(15 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The spectral radius of matrix W x is suggested to be smaller than 1 in [31]. It is shown by [32] that ESNs can be stable if the spectral radius is set to be slightly larger than 1 under some conditions, and recently, a rigorous bound for guaranteeing asymptotic stability of ESN is obtained in [33]. Anyway, the transient property and memory of "reservoir" can be controlled by the initial setting of W x in the preparation phase.…”

Section: Stable Memory and Transient State In The "Reservoir"mentioning

confidence: 99%

Support Vector Echo-State Machine for Chaotic Time-Series Prediction

Shi

Han

2007

IEEE Trans. Neural Netw.

245

109

View full text Add to dashboard Cite

A novel chaotic time series prediction method based on support vector machines and echo state mechanisms is proposed. The basic idea is replacing "kernel trick" with "reservoir trick" in dealing with nonlinearity, that is, performing linear support vector regression in the high dimension "reservoir" state space, and the solution benefits from the advantages from structural risk minimization principle, and we call it SVESMs (Support Vector Echo State Machines). SVESMs belong to a special kind of recurrent neural networks with convex objective function, and its solution is global optimal and unique. SVESMs are especially efficient in dealing with real life nonlinear time series, and its generalization ability and robustness are obtained by regularization operator and robust loss function. The method is tested on the benchmark prediction problem of Mackey-Glass time series and applied to some real life time series such as monthly sunspots time series and runoff time series of the Yellow River, and the prediction results are promising.

show abstract

Section: Stable Memory and Transient State In The "Reservoir"mentioning

confidence: 99%

Support Vector Echo-State Machine for Chaotic Time-Series Prediction

Shi

Han

2007

IEEE Trans. Neural Netw.

245

109

View full text Add to dashboard Cite

show abstract

“…In this work we used a new strategy to find these values; the evolutionary method looks for the best values for the matrices without rescaling the matrices by the spectral radius. The motivation for this consideration was based on others researches specially [2], [12], [13] and [14]. In [2] was said that the condition described above (rescaling the matrices) supply a measure for the computational quality of a reservoir and can all be deduced from the weight matrix of the reservoir, i.e.…”

Section: Reservoir Computingmentioning

confidence: 99%

“…In [13] we were remembered that the idea to rescaling the matrices to adjust the spectral radius within the unit circle in the complex plane come from linear system theory and shows clearly that stability that is necessary to obtain useful responses from linear systems. However, this argument does not necessarily apply to nonlinear systems, the RC case, as demonstrated in [13].…”

Section: Reservoir Computingmentioning

confidence: 99%

See 1 more Smart Citation

Evolutionary strategy for simultaneous optimization of parameters, topology and reservoir weights in Echo State Networks

Ferreira

Ludermir

2010

The 2010 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Reservoir Computing is a new paradigm in artificial recurrent neural network training. A reservoir is generated randomly and only a readout layer is training [1]. Its simplicity and ease of use, paired with its underlying computational power make it an ideal choice for many application domains, for example time-series prediction, speech recognition, noise modeling, dynamic pattern classification, reinforcement learning and language modeling. However it is necessary to adjust the parameters and the topology to create a "good" reservoir for a given application. This paper presents an original investigation of an evolutionary method for simultaneous optimization of parameters, topology and reservoir weights in Echo State Networks. Optimizing reservoirs is a challenge and several evolutionary strategies for optimizing reservoirs have been presented, generally using the idea of separating the topology and reservoir weights to reduce the search space [1]. Here we present a method to optimize everything in concert. The results of this method applied to two different time series are shown and conferred with previous works.

show abstract

“…However, a chaotic reservoir can still be used as long as the input is sufficiently large to drive its dynamics out of the chaotic regime (Ozturk and Principe, 2005).…”

Section: Introductionmentioning

confidence: 99%

Reservoir computing with a chaotic circuit

Jensen¹,

Tufte²

2017

Proceedings of the 14th European Conference on Artificial Life ECAL 2017

View full text Add to dashboard Cite

Reservoir Computing has been highlighted as a promising methodology to perform computation in dynamical systems. This makes Reservoir Computing particularly interesting for exploiting physical systems directly as computing substrates, where the computation happens "for free" in the rich physical domain. In this work we consider a simple chaotic circuit as a reservoir: the Driven Chua's circuit. Its rich variety of available dynamics makes it versatile as a reservoir. At the same time, its simplicity offers insight into what physical properties can be useful for computation. We demonstrate both through simulation and in-circuit experiments, that such a simple circuit can be readily exploited for computation. Our results show excellent performance on two non-temporal tasks. The fact that such a simple nonlinear circuit can be used, suggests that a wide variety of physical systems can be viewed as potential reservoirs.

show abstract

Computing with transiently stable states

Cited by 16 publications

References 5 publications

Support Vector Echo-State Machine for Chaotic Time-Series Prediction

Support Vector Echo-State Machine for Chaotic Time-Series Prediction

Evolutionary strategy for simultaneous optimization of parameters, topology and reservoir weights in Echo State Networks

Reservoir computing with a chaotic circuit

Contact Info

Product

Resources

About