New TERN model improves epidemic forecasting with adaptive memory

Researchers have developed TERN, a novel forecasting model designed to improve the accuracy of predicting epidemic trends, such as influenza. Unlike existing models that treat all past data uniformly, TERN utilizes a delta-rule fast-weight memory that adapts to the epidemic's phase and incorporates an explicit seasonal reference. This approach allows TERN to better leverage historical data from previous seasons while discarding outdated information as the epidemic evolves. In evaluations on influenza benchmarks, TERN demonstrated superior performance compared to established epidemic graph models and general forecasting methods. AI

IMPACT This model's adaptive memory could lead to more accurate public health predictions and resource allocation for epidemics.

RANK_REASON The item is a research paper detailing a new model for epidemic forecasting. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX
• Cola-GNN
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• IArxiv Recommender
• Influence Flower
• ScienceCast

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →