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。
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。
- 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
- 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
- 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
- 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
- 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
- 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
- On one composed backpropagation path, local scalar derivatives are three and four. What is their chain-rule product?
- 七
- 一
- Three quarters
- Twelve
- A shared parameter has loss-gradient contributions two and five through two paths. What combined contribution is accumulated?
- 十
- 七
- 三
- Two fifths