引導式測驗 · 中等 等級

殘差網路測驗

回顧殘差塊運算、恆等快捷方式、梯度路徑、ImageNet 時代的深度以及殘差如何在神經架構中重現。

相關引導路徑殘差網絡
問題 1 的 8

殘差連結具體解決了什麼問題?

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. 殘差連結具體解決了什麼問題?
    • 較深的一般網路訓練效果較淺的網路訓練效果較差(退化)
    • 圖片解析度太低
    • 缺乏標記的訓練數據
    • GPU 記憶體不足
  2. 當輸入和輸出維度匹配時,基本殘差區塊計算什麼?
    • Multiplies the input by itself
    • Adds the block’s learned residual function to its input, y = F(x) + x
    • Drops the input and returns zero
    • Sorts input channels alphabetically
  3. 為什麼跳過連接有助於訓練期間的梯度?
    • They eliminate the need to train weights
    • They force every layer to output zero
    • They provide an additional direct path for gradient flow around the learned transformation
    • They make deep networks immune to all optimization problems
  4. 原始 ImageNet 論文中評估的最深 ResNet 有多深?
    • 18 layers
    • 34 layers
    • 50 layers
    • 152層
  5. 如果殘差塊的層學習 F(x) = 0,那麼區塊會做什麼?
    • 它有效地透過不變的(身分)傳遞輸入
    • 它輸出零並破壞網絡
    • 它使輸入加倍
    • 它隨機化輸出
  6. What residual connection does the Transformer paper describe around attention and feed-forward sublayers?
    • Replace the sublayer input with a class label
    • Add each sublayer’s output to the sublayer input through a residual connection
    • Average every token globally at the output only
    • Remove the residual stream after self-attention
  7. When a residual block changes channel dimensions, what can a projection shortcut do?
    • Convert the input into a text sequence
    • Remove the residual branch
    • Map the shortcut input to the dimensions required for addition
    • Guarantee that every gradient has unit magnitude
  8. What sequence of convolutions defines the original ResNet bottleneck block?
    • Three 3×3 convolutions only
    • A 3×3 convolution followed by two fully connected layers
    • A pooling layer followed by two transposed convolutions
    • A 1×1, then 3×3, then 1×1 convolution