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。
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。
- 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
- 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
- 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
- 原始 ImageNet 論文中評估的最深 ResNet 有多深?
- 18 layers
- 34 layers
- 50 layers
- 152層
- 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
- 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
- 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
- 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