Maswali yanayounganishwa na mwongozo · Kati Kiwango

Maswali ya Mabaki ya Mitandao

Kagua hesabu ya vizuizi vilivyobaki, njia za mkato za utambulisho, njia za gradient, kina cha enzi ya ImageNet, na jinsi mabaki yanavyojirudia katika usanifu wa neva.

Njia za mwongozo zinazohusianaMitandao ya Mabaki
Swali 1 ya 8

Ni shida gani ambayo miunganisho ya mabaki ilisuluhisha haswa?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Ni shida gani ambayo miunganisho ya mabaki ilisuluhisha haswa?
    • Mitandao ya uwazi ya kina mafunzo mbaya zaidi kuliko ile isiyo na kina (uharibifu)
    • Picha zikiwa na mwonekano wa chini sana
    • Upungufu wa data ya mafunzo yenye lebo
    • GPU zinaishiwa na kumbukumbu
  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. Kwa nini kuruka miunganisho husaidia gradient wakati wa mafunzo?
    • 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 tabaka
  5. Ikiwa tabaka za kizuizi cha mabaki hujifunza F(x) = 0, kizuizi hufanya nini?
    • Inapitisha ingizo kwa njia isiyobadilika (kitambulisho)
    • Inatoa sifuri na huvunja mtandao
    • Inaongeza pembejeo mara mbili
    • Inabadilisha matokeo
  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