Previous [ 1] [ 2] [ 3] [ 4] [ 5] [ 6] [ 7] [ 8] [ 9] [ 10] [ 11]

@

Journal of Information Science and Engineering, Vol. 29 No. 4, pp. 695-709 (July 2013)


Visualising Temporal Data Using Reservoir Computing


TZAI-DER WANG AND COLIN FYFE*
Department of Industrial Engineering and Management
Cheng Shiu University
Kaohsiung, 833 Taiwan
*University of the West of Scotland
Paisley, Scotland, UK

We create an artificial neural network which is a version of echo state machines, ESNs. ESNs are recurrent neural networks but unlike most recurrent networks, they come with an efficient training method. We adapt this method using ideas from the neuroscale algorithm so that the network is optimal for projecting multivariate time series data onto a low dimensional manifold so that the structure in the time series can be identified by eye. We illustrate the resulting projections on real and artificial data. Finally we compare visualisation by the technique described herein with visualisation with various standard techniques and demonstrate that the method described in this paper is better.

Keywords: visualisation, echo state machines, multidimensional scaling, reservoir computing, recurrent neural networks

Full Text () Retrieve PDF document (201307_06.pdf)

Received February 6, 2012; accepted June 15, 2012.
Communicated by Chia-Hui Chang.