arXiv cs.LG
· Papers
Scale-Aware Attention for Scarce Neural Data: An RG-Flow Transformer on Sleep-EDF EEG
arXiv:2607.11950v1 Announce Type: new Abstract: Brain field potentials are scale-free: their power spectra follow a $1/f^{beta}$ law whose aperiodic exponent $beta$ tracks cortical state, and sleep depth in particular is a shift in $beta$. We ask whether a transformer endowed with an explicit renormalization-group (