Ikibazo gihuza ibibazo · Hagati Urwego
Imiyoboro isigaye Ikibazo
Ongera usuzume ibisigisigi-byahagaritswe kubara, indangamuntu ngufi, inzira igenda buhoro, ImageNet-ubujyakuzimu, nuburyo ibisigara bisubira mubyububiko.
Ikibazo 1 Bya 8
Ni ikihe kibazo amasano asigaye yakemuye byumwihariko?
Reba buri kibazo8 ibibazo
Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.
- Ni ikihe kibazo amasano asigaye yakemuye byumwihariko?
- Imiyoboro yimbitse yimyitozo iruta iyoroheje (degradation)
- Amashusho kuba make cyane
- Ubuke bwamakuru yanditseho amahugurwa
- GPU yabuze kwibuka
- 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
- 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
- How deep was the deepest ResNet evaluated in the original ImageNet paper?
- 18 layers
- 34 layers
- 50 layers
- Ibice 152
- 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
- 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
- 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
- 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