· Xiaojing Yang · Machine Learning
Overfitting and Regularization
How models learn noise, how validation curves reveal it, and how regularization controls it.
How models learn noise, how validation curves reveal it, and how regularization controls it.
Why preprocessing belongs inside the validation pipeline, not before the split.
A practical guide to splitting data so model evaluation stays honest.
用 bias–variance 诊断 underfitting、overfitting、模型复杂度和泛化问题。
为什么一次划分很脆弱,K-fold 如何工作,以及交叉验证什么时候会在 NLP 中误导我们。
传统 ML 特征如何连接到 embedding、神经网络和现代 NLP 系统。