Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening
This work addresses the challenge of slow feature extraction for researchers in unsupervised learning and temporal data analysis, but it is incremental as it builds on existing Slow Feature Analysis methods.
The paper tackles the problem of extracting temporally slow features from high-dimensional input streams by proposing Power Slow Feature Analysis, a gradient-based variant of Slow Feature Analysis that enables end-to-end training of differentiable architectures, and shows it extracts meaningful low-dimensional features in synthetic, ego-visual, and general similarity-based datasets.
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.