The bias-variance tradeoff (or "bias-variance dilemma")

模式越一般化 (即，它允許其他不同的關係樣式和函數形式越多)，它實效上是該模式去配適(fit)該系統的誤差的可能性越大，結果是配適良好卻預測力很弱。這種偏誤估計量-變異數 (bias-variance)兩難強迫就「過份配適複雜模式的誤差」與「簡單模式的過份簡化」之間做出選擇。

1. Bias-variance tradeoff

   - [ 翻譯此頁 ]
   The bias-variance tradeoff (or "bias-variance dilemma") is a very important issue in data modeling. Ignoring it is a frequent cause of model failure, ...
   www.aiaccess.net/English/.../e_gm_bias_variance.htm - 頁庫存檔 - 類似內容

2. 311: Neural Networks

   - [ 翻譯此頁 ]
   The Bias/Variance Dilemma. One of the most serious problems that arises in connectionist learning by neural networks is overfitting of the provided training ...
   homepages.gold.ac.uk/nikolaev/311over.htm - 頁庫存檔 - 類似內容

3. PDF - Neural Networks and the BiadVariance Dilemma

   - [ 翻譯此頁 ]
   由 S Geman 著作 - 1992 - 被引用 1833 次 - 相關文章
   understood in terms of what we will call the bias/variance dilemma. ... In Section 5, we will discuss further the bias/variance dilemma, and ...