Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening

We propose Power Slow Feature Analysis, a gradient-based method to extract temporally slow features from a high-dimensional input stream that varies on a faster time-scale, as a variant of Slow Feature Analysis (SFA) that allows end-to-end training of arbitrary differentiable architectures and there...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-07
Main Authors: Schüler, Merlin, Hlynsson, Hlynur Davíð, Wiskott, Laurenz
Format: Article
Language:English
Subjects:
Algorithms
Feature extraction
Neural networks
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose Power Slow Feature Analysis, a gradient-based method to extract temporally slow features from a high-dimensional input stream that varies on a faster time-scale, as a variant of Slow Feature Analysis (SFA) that allows end-to-end training of arbitrary differentiable architectures and thereby significantly extends the class of models that can effectively be used for slow feature extraction. We provide experimental evidence that PowerSFA is able to extract meaningful and informative low-dimensional features in the case of (a) synthetic low-dimensional data, (b) ego-visual data, and also for (c) a general dataset for which symmetric non-temporal similarities between points can be defined.
ISSN:2331-8422