引導式測驗 · 中等 等級

反向傳播測驗

測試反向傳播梯度、反向依賴順序、快取前向值、鏈規則乘法、共享路徑和以及最佳化器分離。

相關引導路徑反向傳播
問題 1 的 8

反向傳播計算神經網路相關權重的數量是多少?

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。

  1. 反向傳播計算神經網路相關權重的數量是多少?
    • Derivatives of the loss with respect to those weights
    • A causal percentage of total error uniquely assigned to each weight
    • The architecture drawing without any calculation
    • A permanently updated set of weights without an optimizer
  2. 哪一個數學規則是反向傳播的核心?
    • 畢達哥拉斯定理
    • 貝葉斯定理
    • 微積分的鍊式法則
    • 二次公式
  3. 為什麼反向模式反向傳播可以有效計算許多參數導數?
    • It avoids all local derivatives
    • It reuses graph structure and relevant intermediate results
    • It calculates only the output prediction again
    • It guarantees every implementation has exactly one forward pass of runtime
  4. 反向傳播以什麼順序計算梯度?
    • 從輸入層到輸出層
    • 所有層同時無順序
    • 僅適用於中間隱藏層
    • 從輸出層向後到輸入層
  5. 計算反向傳播梯度本身是否可以確定模型權重已更新?
    • Yes; every backward computation automatically applies a learning rate
    • Yes; gradient values always replace the weights directly
    • No; the optimizer update is a separate step
    • Only if the network has no parameters
  6. In a conventional cached-backpropagation workflow, what does the forward computation provide for later derivative calculations?
    • Relevant intermediate values that can be retained for the backward computation
    • A completed optimizer update without any update rule
    • A guarantee that all later evaluation errors disappear
    • A permanent deletion of the training objective
  7. On one composed backpropagation path, local scalar derivatives are three and four. What is their chain-rule product?
    • 七
    • 一
    • Three quarters
    • Twelve
  8. A shared parameter has loss-gradient contributions two and five through two paths. What combined contribution is accumulated?
    • 十
    • 七
    • 三
    • Two fifths