Residu Reseau Quiz

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Ban jafe-jafe la lëkkaloo residual yi saafara?
   • Taggat reso yu gëna xóot yi ñoo gëna bon ci yi gëna xóotul (degradation)
   • Nataal yi dañu tuuti lool ci dayo
   • ñàkkum done yuñ etikete ci tàggat yaram
   • GPU yi deñuy jeexal mémoire bi
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. Lan moo waral lëkkaloo yi di jàppale gradient yi ci diiru tàggat yaram?
   • 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 lalu
5. Sudee ab diisaayu bloc residuel jàng F(x) = 0, lan la bloc bi di def?
   • Dafay jaar ci duggal gi te du soppiku (dàntite)
   • Dafay génne zero ba noppi di tas reso bi
   • Dafay yokk limu dugal ñaari yoon
   • Dafay aleatoire génne gi
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