Deep Learning for Computer Vision Quiz 2 3 Aug 2025 — Question 5
Show answer
Correct answer
Question 5 of 52 in the IIT Madras BS Deep Learning for Computer Vision (Deep Learning for Computer Vision) Quiz 2 paper sat on 3 Aug 2025, in the May 2025 term (IIT M IMPROVEMENT AN EXAM QIB2 03 Aug 2025). It carries 2 marks.
More questions from this paper
- Figure question
- Which of the following architectures introduced the ROI pooling layer for extracting fixed-size feature maps from varia…
- Which object detection method first integrated a Region Proposal Network (RPN) to generate region proposals within the …
- Which architecture performs object detection as a single regression problem from image pixels to bounding boxes and cla…
- Consider the following statements P and Q regarding AlexNet and choose the correct option: (P) In AlexNet, a trainable …
- Consider two bounding boxes in an image:\ Box A: top-left at (0, 0), bottom-right at (12, 12) - Box B: top-left at (4, …
- Which one of the following statements is True?
- Figure question
- Match the following: | 1) One-to-many RNN architecture | i) Sentiment analysis of Netflix reviews | |---|---| | 2) Many…
- Figure question
- Which of the following techniques help mitigate the vanishing gradient problem in recurrent neural networks?\ Gradient …
- Which of the following techniques help mitigate the exploding gradient problem in recurrent neural networks?\ Gradient …
- Which one of the following statements is false? (Pick the most appropriate one.)
- Which of the following is true regarding Hard Attention and Soft Attention?
- Which of the following are true:
- Consider a Faster R-CNN object detection framework, which is being trained with a mini-batch size of 2. The RPN produce…
- Suppose you want to build an encoder-decoder recurrent model with attention. The context vector at time step t is given…
- Suppose you want to build an encoder-decoder recurrent model with attention. The context vector at time step t is given…
- Consider a Gated Recurrent Unit (GRU) cell at time step ’t’. For each of the entities in the given subquestions, enter …
- Consider a Gated Recurrent Unit (GRU) cell at time step ’t’. For each of the entities in the given subquestions, enter …
- Consider a Gated Recurrent Unit (GRU) cell at time step ’t’. For each of the entities in the given subquestions, enter …
- Consider a Gated Recurrent Unit (GRU) cell at time step ’t’. For each of the entities in the given subquestions, enter …
- Consider a Gated Recurrent Unit (GRU) cell at time step ’t’. For each of the entities in the given subquestions, enter …
- Consider a Gated Recurrent Unit (GRU) cell at time step ’t’. For each of the entities in the given subquestions, enter …
- Number of Parameters:_
- Computational Cost:_
- Number of parameters for depthwise seperable convolution:_
- Computational Cost for depthwise seperable convolution:
- Number of parameters for pointwise convolution:_
- Computational cost for pointwise convolution:
- Number of weights in Weight Matrix U1 is:
- Number of weights in Weight Matrix V1 is:
- Number of weights in Weight Matrix U2 is:
- Number of weights in Weight Matrix V2 is:_
- Number of weights in Weight Matrix W is:_
- e21: _
- e22: _
- e23: _
- α21: _
- α22: _
- α23: _
- c21: _
- c22: _
- e21:_
- e22:_
- e23:_
- α21:_
- α22:_
- α23:_
- c21:_
- c22:_