引導式測驗 · 中等 等級
損失函數測驗
測試預測目標、平方誤差和絕對誤差、類別交叉熵、可用的訓練導數、損失單位和數值誤差平均值。
問題 1 的 8
對於預測任務,其選擇的損失是用來量化什麼相對於訓練目標的?
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。
- 對於預測任務,其選擇的損失是用來量化什麼相對於訓練目標的?
- A specified prediction-error objective
- Only runtime speed
- Only the number of network layers
- Every application benefit automatically
- 哪種損失函數最常用於分類任務?
- 均方誤差
- 平均絕對誤差
- 交叉熵損失
- 僅鉸鏈距離
- 與均方誤差相比,為什麼您會選擇平均絕對誤差?
- 糾正錯誤以給予更多懲罰
- 它對異常值更加穩健,因為它不會平方誤差
- 不能用於回歸
- 它忽略了真正的標籤
- 為什麼基於梯度的訓練需要可使用的損失導數或合適的替代品?
- So a loss number can be printed
- So all learning methods become identical
- So the dataset no longer needs targets
- So backpropagation and optimization can obtain an update signal
- 當指派給目標類別的機率變得非常小時,單熱類別交叉熵會如何變化?
- Its loss must become zero
- It rewards the prediction increasingly
- Its loss becomes large
- It becomes identical to accuracy
- 為什麼準確率通常不直接用作訓練損失?
- 它是不可微分的,因此它沒有給出有用的梯度
- 計算起來太容易了
- 它只適用於回歸
- 無論如何,它總是等於損失
- For illustrative regression residuals one and three, what are mean squared error and mean absolute error?
- MSE is two and MAE is five
- Both are four
- MSE is ten and MAE is four
- MSE is five and MAE is two
- Using a base-two logarithm, what one-hot cross-entropy loss corresponds to target-class probability one-quarter?
- One-quarter bit
- Two bits
- Four bits
- Zero bits