Daily Coding Quiz: Saturday, 21 November 2026
All 10 coding questions with answers and explanations. 1 players took part.
Which technique is the classic way to check if a string of brackets like "({[]})" is balanced?
DSA · easy · 100% of players got it right
- Two pointers
- A stack
- Binary search
- Sorting
Answer: B. A stack
Explanation: Push each opening bracket; on a closing bracket, the top of the stack must be its match. Balanced if the stack ends empty.
What is the worst-case time complexity of linear search?
DSA · easy · 100% of players got it right
- O(1)
- O(log n)
- O(n)
- O(n²)
Answer: C. O(n)
Explanation: If the item is last or missing, every one of the n elements is checked.
Inserting a new node at the head of a singly linked list takes:
DSA · easy · 100% of players got it right
- O(1)
- O(log n)
- O(n)
- O(n log n)
Answer: A. O(1)
Explanation: Point the new node at the current head and make it the head: a constant number of pointer updates.
What does max pooling with a 2×2 window and stride 2 do to a 32 × 32 feature map?
Computer Vision · easy · 100% of players got it right
- Keeps it 32 × 32
- Halves it to 16 × 16, keeping the largest value in each block
- Doubles it to 64 × 64
- Turns it into a single number
Answer: B. Halves it to 16 × 16, keeping the largest value in each block
Explanation: Each non-overlapping 2×2 block becomes one value, the maximum, so height and width are halved.
How many learnable parameters does a 3 × 3 convolution with 64 input channels and 128 output channels (with bias) have?
Computer Vision · medium · 100% of players got it right
- 73,856
- 73,728
- 1,152
- 8,192
Answer: A. 73,856
Explanation: Weights: 3 × 3 × 64 × 128 = 73,728, plus 128 biases = 73,856.
What does Non-Maximum Suppression (NMS) do in object detection?
Computer Vision · medium · 100% of players got it right
- Removes low-resolution images
- Removes duplicate overlapping boxes for the same object, keeping the highest-scoring one
- Normalises pixel values
- Increases the number of anchors
Answer: B. Removes duplicate overlapping boxes for the same object, keeping the highest-scoring one
Explanation: Detectors propose many overlapping boxes. NMS keeps the top box and discards others whose IoU with it exceeds a threshold (often 0.5).
What is the receptive field of one output unit after two stacked 3 × 3 convolutions (stride 1)?
Computer Vision · hard · 100% of players got it right
- 3 × 3
- 5 × 5
- 6 × 6
- 9 × 9
Answer: B. 5 × 5
Explanation: Each extra 3 × 3 layer adds 2. Two of them see 5 × 5 with fewer parameters (2 × 9 = 18 vs 25 per channel pair) and an extra non-linearity: the VGG insight.
What does mAP@0.5:0.95 measure in COCO-style detection evaluation?
Computer Vision · hard · 100% of players got it right
- Accuracy at a single IoU of 0.5
- Mean average precision averaged over IoU thresholds 0.50, 0.55, …, 0.95 and over all classes
- Mean pixel accuracy
- Frames per second
Answer: B. Mean average precision averaged over IoU thresholds 0.50, 0.55, …, 0.95 and over all classes
Explanation: Averaging over strict IoU thresholds rewards precise localisation, not just finding the object. mAP@0.5 (the old PASCAL VOC metric) is more lenient.
Depthwise separable convolution (as in MobileNet) reduces compute by:
Computer Vision · hard · 100% of players got it right
- Using smaller images
- Splitting a standard convolution into a per-channel spatial convolution followed by a 1 × 1 pointwise convolution
- Removing biases
- Quantising weights to 8 bits
Answer: B. Splitting a standard convolution into a per-channel spatial convolution followed by a 1 × 1 pointwise convolution
Explanation: The cost drops roughly by a factor of 1/N + 1/K² (N output channels, K kernel size): about 8–9× fewer operations for 3 × 3 kernels.
Why do 1 × 1 convolutions appear so often in modern CNNs (Inception, ResNet bottlenecks, MobileNet)?
Computer Vision · hard · 100% of players got it right
- They enlarge the receptive field
- They mix channels cheaply, changing the channel count (e.g. to reduce it before an expensive 3 × 3)
- They replace pooling
- They act only as an activation function
Answer: B. They mix channels cheaply, changing the channel count (e.g. to reduce it before an expensive 3 × 3)
Explanation: A 1 × 1 conv is a per-pixel linear layer across channels. Bottlenecks shrink channels, apply the 3 × 3, then expand, cutting compute heavily.
Top 10
- MEDURI BHAGYA LAKSHMI: 232 points (10/10)