arXiv cs.LG· Marvin van Aalst (Computational Life Science, Faculty of Mathematics and Natural Sciences, RWTH Aachen University, Germany), Ad\`ele H. Ribeiro (Causal and Explainable Artificial Intelligence in Life Sciences, Faculty of Mathematics and Natural Sciences, RWTH Aachen University, Germany, Center for Computational Life Sciences, RWTH Aachen University, Germany), Anna Matuszy\'nska (Computational Life Science, Faculty of Mathematics and Natural Sciences, RWTH Aachen University, Germany, Center for Computational Life Sciences, RWTH Aachen University, Germany)·· 16 小时前AI 评分32
当人人都能构建模型：AI 时代的机理推断
When Everyone Can Build a Model: Mechanistic Inference in the Age of AI
AI 导读
现代深度学习与 AI 代码生成大幅降低了生物系统半机理灰盒模型的构建门槛，但预测拟合成功并不代表推断出了真实生物机理。针对生物建模普遍存在的欠定性以及学习组件吸收机理误差的问题，研究提出结合因果推断与集成分析框架。该方法能明确可识别的因果关系并量化不确定性，将单一数据拟合转化为指导后续决策的验证实验。
来源：arXiv cs.LG · arxiv.org