Ikibazo gihuza ibibazo · Hagati Urwego

Imiyoboro isigaye Ikibazo

Ongera usuzume ibisigisigi-byahagaritswe kubara, indangamuntu ngufi, inzira igenda buhoro, ImageNet-ubujyakuzimu, nuburyo ibisigara bisubira mubyububiko.

Inzira zijyanye no kuyoboraImiyoboro isigaye
Ikibazo 1 Bya 8

Ni ikihe kibazo amasano asigaye yakemuye byumwihariko?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Ni ikihe kibazo amasano asigaye yakemuye byumwihariko?
    • Imiyoboro yimbitse yimyitozo iruta iyoroheje (degradation)
    • Amashusho kuba make cyane
    • Ubuke bwamakuru yanditseho amahugurwa
    • GPU yabuze kwibuka
  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. Kuki gusimbuka guhuza bifasha gradients mugihe cy'amahugurwa?
    • 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
    • Ibice 152
  5. Niba ibice bisigaye byiga F (x) = 0, guhagarika gukora iki?
    • Itambutsa neza ibyinjijwe binyuze mubidahindutse (indangamuntu)
    • Isohora zeru kandi isenya umuyoboro
    • Bikubye kabiri ibyinjijwe
    • Ihitamo ibisohoka
  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