Kedis ku xidhan hagaha · Dhexdhexaad Heerka

Kediska Shabakadda Hadhaaga

Dib u eeg xisaabinta xannibaadda haraaga, jid-gaabyada aqoonsiga, dariiqyada gradient-ka, qoto dheer ee ImageNet-era, iyo sida haraaga ugu soo noqnoqdaan naqshadaha neerfaha.

Wadooyinka haga ee la xidhiidhaShabakadaha Hadhaaga ah
Su'aal 1 ee 8

Dhibaato noocee ah ayaa xiriirinta haraaga ah si gaar ah u xalliyeen?

Horudhac su'aal kasta8 su'aalo

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

  1. Dhibaato noocee ah ayaa xiriirinta haraaga ah si gaar ah u xalliyeen?
    • Shabakado cad oo ka qoto dheer oo tababbarka ka sii liita kuwa gaagaaban (hoos u dhac)
    • Sawirada oo xalintoodu aad u hooseyso
    • yaraanta xogta tababarka calaamadeysan
    • GPU-yada xusuusta ayaa ka dhammaanaya
  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. Waa maxay sababta isku-xirnaanta ka boodi ay u caawiso ardayda qalin-jabinta xilliga tababarka?
    • 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 lakab
  5. Haddii lakabyada baloogga ee haraaga ahi bartaan F(x) = 0, muxuu block-gu sameeyaa?
    • Waxay si wax ku ool ah u gudbisaa gelinta iyada oo aan isbeddelin (aqoonsiga)
    • Waxay soo saartaa eber waxayna jebisaa shabakada
    • Waxay labanlaabtaa wax-soo-gelinta
    • Waxay kala soocaysaa wax soo saarka
  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