ScholarGate
助手
Machine learningDeep learning / NLP / CV

可解释多层感知机

可解释多层感知机（Explainable Multilayer Perceptron, XMLP）是一种标准的、通过反向传播训练的前馈神经网络，并辅以事后可解释性技术（如 SHAP 值、LIME 或集成梯度），这些技术将每个预测归因于单个输入特征。这种组合保留了 MLP 的逼近能力，同时满足了在受监管或高风险领域常见的透明度要求。

在 MethodMind 中打开即将推出视频即将推出Download slides

阅读完整方法

仅限会员

使用免费账户登录即可阅读本节。

登录

Method map

The neighbourhood of related methods — select a node to explore.

可解释多层感知机
可解释长短期记忆网络可解释 Transformer多层感知机 (MLP)随机森林

来源

  1. Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774. link ↗
  2. Explainable artificial intelligence. Wikipedia. link ↗

如何引用本页

ScholarGate. (2026, June 3). Explainable Multilayer Perceptron (MLP with Post-hoc Interpretability). ScholarGate. https://scholargate.app/zh/deep-learning/explainable-multilayer-perceptron

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side →

发现本页有问题？报告或提出修改建议 →

ScholarGate — Explainable Multilayer Perceptron (Explainable Multilayer Perceptron (MLP with Post-hoc Interpretability)). 于 2026-06-15 检索自 https://scholargate.app/zh/deep-learning/explainable-multilayer-perceptron · 数据集： https://doi.org/10.5281/zenodo.20539026