Kuis Jaringan Sisa

Jawaban dan penjelasan muncul saat Anda mengikuti kuis.

1. Masalah apa yang secara spesifik dipecahkan oleh koneksi sisa?
   • Pelatihan jaringan biasa yang lebih dalam lebih buruk daripada jaringan yang lebih dangkal (degradasi)
   • Gambar beresolusi terlalu rendah
   • Kekurangan data pelatihan berlabel
   • GPU kehabisan memori
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. Mengapa lewati koneksi membantu gradien selama pelatihan?
   • 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 lapisan
5. Jika lapisan blok sisa mengetahui F(x) = 0, apa yang dilakukan blok tersebut?
   • Ini secara efektif meneruskan input melalui perubahan (identitas)
   • Ini menghasilkan nol dan memutus jaringan
   • Ini menggandakan masukan
   • Ini mengacak output
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