ResNet MCQ 15 Questions
Time: ~25 mins Advanced

ResNet MCQ

Identity shortcuts let gradients flow and enable networks with tens or hundreds of layers.

Easy: 5 Q Medium: 6 Q Hard: 4 Q
Residual

F(x)+x

Skip

Identity path

Bottleneck

1×1–3×3–1×1

Depth

50–152+ layers

Residual learning

ResNet replaces a stack of layers learning H(x) with residual blocks learning F(x) such that output is F(x)+x when shapes match. Identity shortcuts propagate gradients and ease optimization, enabling much deeper networks on ImageNet and detection backbones.

Why F(x)+x

If the desired mapping is close to identity, learning small perturbations F is easier than learning a full mapping from scratch.

Key ideas

Residual block

Two or three conv layers plus a shortcut summing with the input.

Projection shortcut

1×1 conv on x when channel or spatial sizes change.

Bottleneck

Reduces cost: narrow → 3×3 → narrow channels per block.

Batch norm

Stabilizes training of very deep stacks (used in original ResNet).

Deep stack

stem → stage of residual blocks → global pool → FC / detection head

Pro tip: When implementing, verify tensor shapes: mismatched H×W or C needs projection conv on the shortcut.