Learning persistent dynamics with neural networks.

Persistence is one of the most common characteristics of real-world time series. In this work we investigate the process of learning persistent dynamics by neural networks. We show that for chaotic times series the network can get stuck for long training periods in a trivial minimum of the error function related to the long-term autocorrelation in the series.

Nonstationary time-series analysis: accurate reconstruction of driving forces.

We propose a simple method for the accurate reconstruction of slowly changing external forces acting on nonlinear dynamical systems. The method traces the evolution of the external force by locally linearizing the map dependency with the shifting parameter. Application of our algorithm to synthetic data corresponding to discrete models of evolving ecosystems shows an accuracy that outperforms those of previous methods in the literature.

A late-stopping method for optimal aggregation of neural networks.

Ensembles of artificial neural networks have been used in the last years as classification/regression machines, showing improved generalization capabilities that outperform those of single networks. However, it has been recognized that for aggregation to be effective the individual networks must be as accurate and diverse as possible. An important problem is, then, how to tune the aggregate members in order to have an optimal compromise between these two conflicting conditions.

Automatic digital processing in speckle photography: comparison of two algorithms.

Two algorithms for analyzing speckle photography fringes for spacing and orientation using a digital image processing system are compared. Each algorithm was tested for accuracy and computer run-time through a computer simulation which includes the degradation of data by noise.

Two-dimensional digital processing of speckle photography fringes. 3: Accuracy in angular determination.

The performance of a previously published algorithm for the determination of the direction of speckle photography fringes is evaluated through computer simulation. Numerical results indicate that even in the extreme cases of patterns with very low fringe densities and visibilities contaminated with high noise levels, fringe direction can be determined with a fair degree of accuracy (0.5 degrees ).