Guide-yakabatana mibvunzo · Pakati Nhanho

Residual Networks Quiz

Review residual-block computation, identity shortcuts, gradient paths, ImageNet-era depth, and how residuals recur in neural architectures.

Nzira dzekutungamira dzinoenderanaResidual Networks
Mubvunzo 1 ye 8

Nderipi dambudziko rakasara rakanyatsogadziriswa?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Nderipi dambudziko rakasara rakanyatsogadziriswa?
    • Yakadzika plain network kudzidziswa kwakaipa kupfuura kudzika (kuderera)
    • Mifananidzo iri kuderera zvakanyanya
    • Kushomeka kwedata rekudzidziswa rakanyorwa
    • maGPU ari kupera mundangariro
  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. Sei kusvetuka kubatanidza kuchibatsira gradients panguva yekudzidziswa?
    • 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
    • 152 layers
  5. Kana masara echivharo akaturikidzana akadzidza F(x) = 0, bhuroko rinoitei?
    • Iyo inonyatso pfuura iyo yekuisa kuburikidza isina kuchinjika (kuzivikanwa)
    • Inoburitsa zero uye inotyora network
    • Inowedzera zvakapetwa kaviri
    • Inoita randomizes zvinobuda
  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