引導式測驗 · 中等 等級
模型漂移檢測測驗
檢視資料和概念漂移、分佈監控、KS 比較、延遲標籤以及對漂移警報的仔細回應。
問題 1 的 8
資料漂移和概念漂移有什麼差別?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 資料漂移和概念漂移有什麼差別?
- 資料漂移改變了輸入的分佈;概念漂移改變了輸入與輸出的關係
- 它們是同一件事的兩個名稱
- 資料漂移僅影響影像;概念漂移只影響文本
- 訓練時會發生資料漂移;測試中發生概念漂移
- 團隊如何解讀 PSI 值如 0.30?
- As a guarantee that model accuracy has fallen
- As a signal to investigate under the chosen monitoring policy, not a universal proof of harmful drift
- As an identical threshold for every feature and population
- As proof that retraining must begin immediately
- 為什麼基於輸入的漂移偵測可以提前預警?
- 因為先輸入總是錯誤的
- 因為輸入是較小的文件
- 因為真實標籤通常比預測晚得多
- 因為模型完全忽略標籤
- 兩樣本 Kolmogorov‑Smirnov 檢定比較什麼?
- The average accuracy of two classifiers only
- The class labels predicted by a single model
- The parameter values of two neural networks
- The empirical cumulative distribution functions of two samples
- 哪一種情況是概念漂移的明顯例子?
- 即使是外觀相似的電子郵件,使用者認為的「垃圾郵件」也會隨著時間而變化
- 相機產生稍微明亮的影像
- 資料集中的客戶年齡保持不變
- 資料集以新的文件格式儲存
- What is a safe first response when an input-drift monitor triggers?
- Automatically deploy a newly retrained model without evaluation
- Investigate the data and impact, then decide whether retraining or another action is justified
- Delete the reference data
- Assume every shift is harmful concept drift
- What can TensorFlow Data Validation check in an ML pipeline?
- The causal effect of a feature
- Whether every model prediction is correct
- Data schemas and statistics, including unexpected changes
- The absolute accuracy of an unlabeled dataset
- What does the Population Stability Index (PSI) measure in a drift-monitoring setup?
- The model’s accuracy on labeled examples
- A causal effect of an input feature
- A universal pass/fail threshold for all models
- A numerical summary of how binned feature distributions differ between reference and current data