Kuiz berkaitan panduan · Sederhana Tahap

Kuiz Rangkaian Sisa

Semak pengiraan blok baki, pintasan identiti, laluan kecerunan, kedalaman era ImageNet dan cara baki berulang dalam seni bina saraf.

Laluan panduan yang berkaitanRangkaian Sisa
soalan 1 daripada 8

Apakah masalah yang diselesaikan secara khusus oleh sambungan baki?

Pratonton setiap soalan8 soalan

Jawapan dan penjelasan muncul semasa anda mengambil kuiz.

  1. Apakah masalah yang diselesaikan secara khusus oleh sambungan baki?
    • Latihan rangkaian biasa yang lebih dalam lebih teruk daripada yang lebih cetek (degradasi)
    • Imej menjadi peleraian terlalu rendah
    • Kekurangan data latihan 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 sambungan langkau membantu kecerunan semasa latihan?
    • 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 baki belajar F(x) = 0, apakah yang dilakukan oleh bongkah itu?
    • Ia berkesan menghantar input melalui tidak berubah (identiti)
    • Ia mengeluarkan sifar dan memecahkan rangkaian
    • Ia menggandakan input
    • Ia secara rawak 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