We introduce a new data-driven method, feature-based slow feature analysis (f-SFA), to track non-stationarity from time-series data (with no generative model).
It beats benchmarks on chaotic systems and tracks sleep depth continuously from EEG.
arxiv.org/abs/2609.01651
We introduce a new data-driven method, feature-based slow feature analysis (f-SFA), to track non-stationarity from time-series data (with no generative model).
It beats benchmarks on chaotic systems and tracks sleep depth continuously from EEG.
arxiv.org/abs/2609.01651
www.thetransmitter.org/early-career...
www.thetransmitter.org/early-career...