研究人员开发了ATHENA，一个新颖的、基于知识引导的代理神经架构搜索（NAS）框架，专门用于基于Transformer的电子健康记录（EHR）建模。该框架旨在通过利用权重共享的超网和两层跨医院架构先验来减少这些模型通常需要的大量手动调整。ATHENA在六项临床预测任务和两个健康系统上，与四个NAS基线相比，表现出具有竞争力或更优的性能，并显示出更一致的架构选择。 AI
影响 该框架可以显著减少优化用于临床预测任务的Transformer模型的手动工作量和计算成本。
排序理由 该集群描述了一个发表在arXiv上的新颖研究框架。
在 arXiv cs.MA (Multiagent) 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2608.21712v1 Announce Type: new Abstract: Transformer-based models are widely used for clinical prediction from electronic health records (EHRs), yet their architectures still require substantial manual tuning, and the optimal configuration may vary across tasks and hospita…
Transformer-based models are widely used for clinical prediction from electronic health records (EHRs), yet their architectures still require substantial manual tuning, and the optimal configuration may vary across tasks and hospitals. Neural architecture search (NAS) automates a…
Transformer-based models are widely used for clinical prediction from electronic health records (EHRs), yet their architectures require manual tuning, and the optimal configuration may vary across tasks and hospitals. Neural architecture search (NAS) automates architecture design…