Google Research 播客解读 20 万行代码的流感预测模型
Google Research 亲口讲他们怎么用 20 万行代码的模型把流感和 RSV 住院预测做得比传统方法还准,做法讲得挺细。
Google Research 在播客中由 Michael Brenner 与 Lizzie Dorfman 介绍一个约 20 万行代码的 AI 模型,用于预测流感与 RSV 的住院人数。该模型在预测准确率上超过了传统流感预测方法。节目由 Sinead Bovell 主持,讨论了模型的构建思路与实际表现。
How did 200k lines of code outperform traditional flu forecasting? 📊🩺
On the @GoogleResearch Podcast, @SineadBovell, Michael Brenner & Lizzie Dorfman discuss how an AI model achieved top accuracy for flu & RSV hospitalizations.
🎬 Watch: https://t.co/jZgbKCoypP https://t.co/KQ4tGV6c6W