Quantitative evaluation of the performance of discrete-time reservoir computers in the forecasting, filtering, and reconstruction of stochastic stationary signals
This work addresses forecasting and filtering challenges in stochastic time series analysis, offering improved performance for applications in signal processing, but it is incremental as it builds on existing reservoir computing frameworks.
The paper tackles the problem of forecasting, filtering, and reconstructing stochastic stationary signals using reservoir computing, extending information processing capacity to non-independent inputs and showing that this approach significantly outperforms standard techniques in some cases.
This paper extends the notion of information processing capacity for non-independent input signals in the context of reservoir computing (RC). The presence of input autocorrelation makes worthwhile the treatment of forecasting and filtering problems for which we explicitly compute this generalized capacity as a function of the reservoir parameter values using a streamlined model. The reservoir model leading to these developments is used to show that, whenever that approximation is valid, this computational paradigm satisfies the so called separation and fading memory properties that are usually associated with good information processing performances. We show that several standard memory, forecasting, and filtering problems that appear in the parametric stochastic time series context can be readily formulated and tackled via RC which, as we show, significantly outperforms standard techniques in some instances.