Autoencoding Ground Motion Data for Visualisation

Gianniotis, Nikolaos; Riggelsen, Carsten; Kühn, Nicolas; Scherbaum, Frank

doi:10.1007/978-3-642-33266-1_49

Cited by 2 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [5] seismic ground motion data are visualised using a modified autoencoder. The outputs of the autoencoder were Fig.…”

Section: Autoencoder For Seismic Ground Motion Datamentioning

confidence: 99%

“…In the same spirit, [4] described a method for the topographic organisation of astronomical fluxes, which took into account the physical model underlying the data. In [5] a modified autoencoder [6] is described for visualising data in a geophysical domain. The outputs of the autoencoder were coupled to a physical model, thus forcing the autoencoder to output physically constrained reconstructions for the inputs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Interpretable magnification factors for topographic maps of high dimensional and structured data

Gianniotis

2013

2013 IEEE Symposium on Computational Intelligence and Data Mining (CIDM)

Self Cite

View full text Add to dashboard Cite

Visualisation of high-dimensional data is typically formulated as a non-linear mapping between a high-dimensional space and a two-dimensional latent space. The goal is that similar data items should be projected to similar coordinates in the latent space. Nevertheless, due to the non-linearity data items that are distant in the high-dimensional space may be projected close to each other in the latent space. Therefore, magnification factors must be analysed in order to detect stretches and contractions in the embedded latent space. However, magnification factors may not be straightforward to communicate to practitioners who are not aware of such manifestations in the embedded latent space, and only care about an accurate depiction that shows which data items are similar. The goal of this work is to devise a more convenient visualisation that corrects for magnifications and thus depicts the true distances between data items more faithfully. We present an approach based on a multidimensional scaling technique that corrects the obtained visualisations by distorting them according to local magnification factors. The approach is general and we demonstrate it on different visualisation algorithms, such as GTM extensions, the autoencoder, the GP-LVM, and on different types of data.

show abstract

“…In [5] seismic ground motion data are visualised using a modified autoencoder. The outputs of the autoencoder were Fig.…”

Section: Autoencoder For Seismic Ground Motion Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Interpretable magnification factors for topographic maps of high dimensional and structured data

Gianniotis

2013

2013 IEEE Symposium on Computational Intelligence and Data Mining (CIDM)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The gradient of the new objective function in Eq. (7) with respect to the weights θ, is calculated by backpropagation [2]. We use L-BFGS as the optimisation routine for training the weights θ.…”

Section: Esn-coupled Autoencodermentioning

confidence: 99%

“…In this work, we employ the ESN in the formulation of a dimensionality reduction algorithm for visualising a dataset of time series (we extend previous work presented in [7]). Given a fixed reservoir, the only free parameters in the ESN are in the readout weight vector which maps the state space to the sequence space.…”

Section: Introductionmentioning

confidence: 99%

Model-coupled autoencoder for time series visualisation

et al. 2016

Self Cite

View full text Add to dashboard Cite

We present an approach for the visualisation of a set of time series that combines an echo state network with an autoencoder. For each time series in the dataset we train an echo state network, using a common and fixed reservoir of hidden neurons, and use the optimised readout weights as the new representation. Dimensionality reduction is then performed via an autoencoder on the readout weight representations. The crux of the work is to equip the autoencoder with a loss function that correctly interprets the reconstructed readout weights by associating them with a reconstruction error measured in the data space of sequences. This essentially amounts to measuring the predictive performance that the reconstructed readout weights exhibit on their corresponding sequences when plugged back into the echo state network with the same fixed reservoir. We demonstrate that the proposed visualisation framework can deal both with real valued sequences as well as binary sequences. We derive magnification factors in order to analyse distance preservations and distortions in the visualisation space. The versatility and advantages of the proposed method are demonstrated on datasets of time series that originate from diverse domains.

show abstract

Autoencoding Ground Motion Data for Visualisation

Cited by 2 publications

References 10 publications

Interpretable magnification factors for topographic maps of high dimensional and structured data

Interpretable magnification factors for topographic maps of high dimensional and structured data

Model-coupled autoencoder for time series visualisation

Contact Info

Product

Resources

About