PulseAugur
中
实时 10:06:58
English(EN) Self-explainable Operator Learning for Discovering Spatial Patterns in Functional Data

新框架使算子学习模型具有自解释性

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员开发了一种新的自解释算子学习框架，增强了函数数据分析中使用的神经网络模型的可解释性。该框架将算子学习重新构建为广义函数线性模型，从而可以将输入域分解为子域。通过计算局部积分，模型可以精确定位对预测有贡献的特定输入区域，从而将空间特征与输出模式联系起来。这种嵌入式可解释性提供了一种透明且物理上可解释的方法，特别适用于流体流动问题等科学应用，并且与已建立的事后方法在定性上是一致的。 AI

影响 增强了科学应用中机器学习模型的可解释性，从而建立了信任并实现了更明智的数据驱动分析。

排序理由 该集群包含一篇详细介绍算子学习新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新框架使算子学习模型具有自解释性

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Mojgan Alishiri, Amirhossein Arzani ·

    Self-explainable Operator Learning for Discovering Spatial Patterns in Functional Data

    arXiv:2607.02203v1 Announce Type: new Abstract: Operator learning has emerged as a powerful tool for modeling complex physical systems in functional spaces. However, their neural network-based architectures make them opaque models, obscuring the reasoning behind their predictions…

  2. arXiv cs.LG TIER_1 English(EN) · Amirhossein Arzani ·

    Self-explainable Operator Learning for Discovering Spatial Patterns in Functional Data

    Operator learning has emerged as a powerful tool for modeling complex physical systems in functional spaces. However, their neural network-based architectures make them opaque models, obscuring the reasoning behind their predictions. In this work, we introduce a self-explainable …

相关话题