引導式測驗 · 中等 等級

梯度消失和爆炸測驗

檢視鍊式法則梯度積、飽和度、循環序列長度、剩餘路徑和光譜半徑啟發法的限制。

相關引導路徑梯度消失和爆炸
問題 1 的 8

反向傳播中的什麼數學運算是梯度消失和爆炸的根本原因?

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. 反向傳播中的什麼數學運算是梯度消失和爆炸的根本原因?
    • 透過鍊式法則重複乘以每層因子
    • 在單層上新增漸變
    • 將損失除以批量大小
    • 取權重的平方根
  2. Why can sigmoid or tanh units contribute to vanishing gradients when they are saturated?
    • Their derivatives are always larger than one
    • Their derivatives become small in saturated regions, so repeated chain-rule products can shrink
    • They remove the chain rule from backpropagation
    • They force every weight to zero
  3. 哪一種架構受長序列梯度問題的影響最嚴重?
    • 兩層感知器
    • 單一線性迴歸
    • 循環神經網路在多個時間步上展開
    • 一個查找表
  4. 看到訓練損失突然變成 NaN 最有可能顯示哪個問題?
    • 梯度消失
    • 完美融合
    • 學習率太小
    • 梯度爆炸
  5. 殘餘(跳過)連接如何幫助解決梯度消失問題?
    • 他們為梯度提供了一條直接向後的捷徑,繞過了縮小乘法
    • 他們消除了所有非線性
    • 他們自動提高學習率
    • 他們刪除早期圖層
  6. In a simplified analysis of a recurrent linear transformation repeated over many steps, what matrix quantity is a rough signal of growth versus decay?
    • The matrix trace relative to the batch size
    • The spectral radius relative to one
    • The number of hidden units alone
    • The determinant relative to the learning rate
  7. A backpropagated gradient is multiplied by a factor below one at each of many layers. What trend should you expect?
    • It must become exactly one
    • It grows exponentially regardless of the factor
    • The signal can shrink exponentially with depth
    • It stops depending on earlier layers after one step
  8. Why can a recurrent network be especially vulnerable over a long sequence?
    • The network has no hidden state
    • The output layer is used only once
    • The sequence is processed without a chain rule
    • The recurrent transformation is applied repeatedly across timesteps, compounding its gradient effect