index 2ecd1b9..c4bb193 100644
@@ -17,4 +17,6 @@ a self-supervised approach to cleaning neural signals — specifically removing
the self-supervised framing is the interesting technical angle. instead of training a model to classify "artifact" vs "clean" with labeled examples (which require expert annotation), you use the structure of EEG itself — temporal consistency, spatial correlations between electrodes, known frequency properties of real neural signals — as a self-supervision signal. the model learns what "clean" looks like without being told, then can detect and remove deviations. similar approaches have worked well in other time-series domains.
-this sits at the intersection of several interests: ML for biosignals (→ [[ppg-biomarker-wearable|PPG biomarker wearable]]), hardware for sensing (→ [[sensor-capturer|sensor capturer]]), and BCI more broadly (→ [[emg-bracelet|EMG bracelet]], [[pupilometry-glasses|pupilometry glasses]]). the research angle would fit well as a paper or an open-source tool — there's a clear gap in the literature for robust self-supervised artifact rejection that generalizes across datasets and electrode configurations. also connects to [[symbolic-regression|symbolic regression]] as another signal-processing research direction.
\ No newline at end of file
+this sits at the intersection of several interests: ML for biosignals, hardware for sensing (→ [[sensor-capturer|sensor capturer]]), and BCI more broadly (→ [[emg-bracelet|EMG bracelet]], [[pupilometry-glasses|pupilometry glasses]]). the research angle would fit well as a paper or an open-source tool — there's a clear gap in the literature for robust self-supervised artifact rejection that generalizes across datasets and electrode configurations.
+
+related: [[symbolic-regression|symbolic regression]]
\ No newline at end of file