Idanwo ti o sopọ mọ itọsọna · Alabọde Ipele

Wíwọ Networks adanwo

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

Jẹmọ itọsọna awọn ọnaAwọn nẹtiwọki ti o ku
Ibeere 1 ti 8

Isoro wo ni awọn asopọ to ku ni pato yanju?

Awotẹlẹ gbogbo ibeere8 ibeere

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

  1. Isoro wo ni awọn asopọ to ku ni pato yanju?
    • Ikẹkọ awọn nẹtiwọọki pẹtẹlẹ ti o buru ju awọn ti aijinile (ibajẹ)
    • Awọn aworan jẹ ipinnu kekere pupọ
    • Aito ti ike data ikẹkọ
    • GPUs nṣiṣẹ jade ti iranti
  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. Kini idi ti awọn asopọ foju ṣe iranlọwọ awọn gradients lakoko ikẹkọ?
    • 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 fẹlẹfẹlẹ
  5. Ti awọn ipele bulọọki iyokù kọ F(x) = 0, kini idina naa ṣe?
    • O ṣe imunadoko kikọ sii nipasẹ aiyipada (idanimọ)
    • O jade odo o si fọ nẹtiwọọki naa
    • O sekeji awọn input
    • O randomizes awọn o wu
  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