引導式測驗 · 中等 等級
半監督學習測驗
檢視混合標籤可用性、自我訓練、一致性、聚類假設、FixMatch、錯誤強化、圖傳播和未標記標記。
問題 1 的 8
半監督學習專為以下情況而設計:
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。
- 半監督學習專為以下情況而設計:
- 每個例子都有完整的標籤
- 您根本沒有數據
- 獲得標籤的成本極其低廉
- 您有一些標記數據和大量未標記數據
- 自訓練如何在未標記的範例上使用選定的預測?
- It treats selected model guesses as pseudo-labels for further fitting
- It converts every guess into a verified human annotation
- It permanently removes the original labeled examples by definition
- It chooses labels only from alphabetical order
- 在一致性正則化下,在所選的類別保留增強之間鼓勵達成什麼協議?
- A requirement that every arbitrary edit preserve the class
- Opposite predictions for every view of an example
- Agreement in the model's predictions
- Removal of every unlabeled input from the loss
- 對於半監督方法中的分組觀察,聚類假設提出了什麼?
- Every possible cluster must contain every class equally
- They are likely to share a label under the assumed data structure
- All semi-supervised methods guarantee identical clusters
- Labels are determined by filename order
- FixMatch 如何結合這兩個主要思想?
- 它對弱增強輸入進行偽標記,然後訓練強增強版本以匹配
- 它僅使用標記數據並忽略其他所有內容
- 它完全刪除了增強
- 它純粹隨機分配標籤
- 在偽標籤訓練過程中如何會出現確認偏誤?
- Only low-confidence labels can ever be wrong
- Every selected prediction becomes a verified fact
- Using any verified label prevents the model from learning
- Incorrect model-generated labels are accepted and then reinforced
- Which structure distinguishes graph-based label propagation from repeatedly selecting a classifier's confident guesses?
- Only a threshold on independently predicted class probabilities
- A similarity graph over labeled and unlabeled observations
- A list of random output labels with no input similarities
- A requirement to discard every relationship between observations
- In the stated scikit-learn semi-supervised interface, which integer marks an unlabeled target entry?
- Zero, necessarily the first actual class label
- One, necessarily the second actual class label
- Minus one
- Fifty, interpreted as a percentage-confidence threshold