Please use this identifier to cite or link to this item:
|Title||Reservoir computing and data visualisation|
We consider the problem of visualisation of high dimensional multivariate time series. A data analyst in creating a two dimensional projection of such a time series might hope to gain some intuition into the structure of the original high dimensional data set. We review a method for visualising time series data using an extension of Echo State Networks (ESNs). The method uses the multidimensional scaling criterion in order to create a visualisation of the time series after its representation in the reservoir of the ESN. We illustrate the method with two dimensional maps of a financial time series. The method is then compared with a mapping which uses a fixed latent space and a novel objective function.
|Published in||Journal of Artificial Intelligence and Soft Computing Research|
|Item link||Item Link|
|Files in this item|
|Ashour, Wesam M._69.pdf||603.5Kb|