Factors important for good visualisation of time series. (2016)

• Record Type: Journal Article
• Authors: Wang, Tzai-Der; Wu, Xiaochuan; Fyfe, Colin
• Is Part Of: International journal of computational science and engineering. Volume 12:Number 1(2016)
• Page Start: 17
• Page End: 28
• Publication Date: 2016
• Subjects: echo state machines -- visualisation -- multidimensional scaling -- time series -- artificial neural networks -- ANNs; Computer science -- Mathematics -- Periodicals; Computer simulation -- Mathematical aspects -- Periodicals; Computational intelligence -- Periodicals; 004.015105
• Languages: English
• ISSNs: 1742-7185

Abstract

We create an artificial neural network which is a version of echo state networks, ESNs. ESNs are recurrent neural networks but unlike most recurrent networks, they come with an efficient training method. We have previously (Wang et al., 2011) adapted this method using ideas from neuroscale (Tipping, 1996) so that the network can be used for projecting multivariate time series data onto a low dimensional manifold so that the structure in the time series can be identified by eye. In this paper, we review work on a minimal architecture echo state machine (Wang et al., 2011) in the context of visualisation and show that it does not perform as well as the original. We then discuss three factors which may affect the capability of the network - its structure, size and sparsity - and show that, of these three, by far the most important is the size of the reservoir of neurons.