TERN: A Delta-rule Memory with a Seasonal Reference and Online Adaptation for Epidemic Forecasting
TERN, a forecaster built around a delta-rule fast-weight memory that decays channel-wise and erases along a learned address under gates driven by local epidemic-phase features, is proposed, combined with an explicit seasonal reference and online adaptation.
Shunya Nagashima, Yuta Funayama
· 0 citations