← Back to all news
arXiv AI By Shunya Nagashima, Yuta Funayama

TERN: A Delta-rule Memory with a Seasonal Reference and Online Adaptation for Epidemic Forecasting

Read the original on arXiv AI →

The paper introduces TERN, a forecasting model that uses a delta‑rule fast‑weight memory with channel‑wise decay and learned erasure gates, combined with a seasonal reference and online adaptation. It addresses challenges in influenza forecasting such as limited seasonal data, shifting wave patterns, and misleading information after peaks. On three Cola‑GNN influenza benchmarks, TERN outperformed existing epidemic graph models and general forecasters, matching or exceeding seasonal references and demonstrating the value of its memory component.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Sep 15

Generative diffusion models for spatiotemporal influenza forecasting

The paper introduces Influpaint, a denoising diffusion probabilistic model adapted for forecasting influenza incidence. By representing influenza seasons as spatiotemporal images and training on a hybrid dataset of surveillance and simulated trajectories, the model learns a rich distribution of disease dynamics and performs forecasting as a conditional generation task. In retrospective and real‑time evaluations, Influpaint produces realistic, diverse epidemic trajectories and achieves forecast accuracy competitive with leading ensemble methods, especially when trained with 30% surveillance and 70% simulated data.

By Joseph Lemaitre, Justin Lessler
diffusionmultimodal
More like this →