잔여 네트워크 퀴즈

퀴즈를 풀면 정답과 설명이 나타납니다.

1. 잔여 연결이 구체적으로 어떤 문제를 해결했습니까?
   • 얕은 네트워크보다 더 깊은 일반 네트워크 훈련이 더 나쁨(성능 저하)
   • 이미지 해상도가 너무 낮음
   • 레이블이 지정된 훈련 데이터 부족
   • GPU 메모리 부족
2. What does a basic residual block compute when input and output dimensions match?
   • 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. 훈련 중에 연결 건너뛰기가 경사도에 도움이 되는 이유는 무엇입니까?
   • 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. How deep was the deepest ResNet evaluated in the original ImageNet paper?
   • 18 layers
   • 34 layers
   • 50 layers
   • 152개 레이어
5. 잔차 블록의 레이어가 F(x) = 0을 학습하면 블록은 무엇을 합니까?
   • 입력을 변경되지 않은 (ID)을 통해 효과적으로 전달합니다.
   • 0을 출력하고 네트워크를 중단시킵니다.
   • 입력이 두 배로 늘어납니다.
   • 출력을 무작위로 지정합니다.
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