Machine learningTrustworthy ML
分布外检测
分布外（OOD）检测是一系列技术，用于识别已部署的机器学习模型何时接收到与其训练数据分布显著不同的输入。该问题由 Hendrycks 和 Gimpel 于 2017 年正式提出，这些方法使模型能够标记不熟悉的输入，而不是默默地产生不可靠的预测，从而使其成为高风险领域中值得信赖和安全的人工智能部署的基础。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Hendrycks, D., & Gimpel, K. (2017). A baseline for detecting misclassified and out-of-distribution examples in neural networks. International Conference on Learning Representations. link ↗
如何引用本页
ScholarGate. (2026, June 2). Out-of-Distribution Detection. ScholarGate. https://scholargate.app/zh/machine-learning/out-of-distribution-detection
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 →