Share Email Print
cover

Proceedings Paper

Dimensionality reduction for nonlinear time series
Author(s): David DeMers
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

A technique for recoding multidimensional data in a representation of reduced dimensionality is presented. A non-linear encoder-decoder for multidimensional data with compact representations is developed. The technique of training a neural network to learn the identity map through a `bottleneck' is extended to networks with non-linear representations, and an objective function which penalizes entropy of the hidden unit activations is shown to result in low dimensional encodings. For scalar time series data, a common technique is phase-space reconstruction by embedding the time-lagged scalar signal in a higher dimensional space. Choosing the proper embedding dimension is difficult. By using non-linear dimensionality reduction, the intrinsic dimensionality of the underlying system may be estimated.

Paper Details

Date Published: 16 December 1992
PDF: 12 pages
Proc. SPIE 1766, Neural and Stochastic Methods in Image and Signal Processing, (16 December 1992); doi: 10.1117/12.130829
Show Author Affiliations
David DeMers, Univ. of California/San Diego (United States)


Published in SPIE Proceedings Vol. 1766:
Neural and Stochastic Methods in Image and Signal Processing
Su-Shing Chen, Editor(s)

© SPIE. Terms of Use
Back to Top