Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.
0 / 29 published solutions
Question 117 MCQ · 2.0 marks
Which one of the below statements is incorrect?
6406532878458.
Global Average Pooling (GAP) technique is used in both CAM and Grad-CAM.
6406532878459.
The purpose of GAP is to find an importance score for every feature map,
which represents how much that feature map contributes to generate the explanation.
6406532878460.
For both CAM and Grad-CAM, explanation can be generated with respect to
any layer of a CNN.
6406532878461.
For every pixel in the feature map, Grad-CAM++ assigns different weightage,
whereas Grad-CAM gives the same weightage.
A published solution is not available for this question yet.
Which of the following is incorrect for the reparametrization trick used in a Variational
AutoEncoder (VAE)?
6406532878484.
This technique is used, since the expected reconstruction error requires
estimation by sampling which has very high variance.
6406532878485.
It can be applied to any “location-scale” family of distributions where the
location (mean) and scale (variance) of the standard version is 0 and 1.
6406532878486.
The reparametrization trick is applicable to continuous distributions as well as
discrete distributions.
6406532878487.
It allows the random variable to be expressed as a different transformation of
auxiliary variables which helps the gradient estimation with only one sample
A published solution is not available for this question yet.
The goal of triplet loss is to ensure that the distance between the anchor and
the negative sample is at least ’margin’ less than the distance between anchor and positive
sample.
6406532878510.
Face identification is a multi-class classification problem whereas face
verification is a binary classification problem
6406532878511.
Both the goal of triplet loss is to ensure that the distance between the anchor
and the negative sample is at least ’margin’ less than the distance between anchor and positive
sample. & Face identification is a multi-class classification problem whereas face verification is a
binary classification problem
6406532878512.
None of these
A published solution is not available for this question yet.
Consider two 10×10 bounding boxes(one on the upper left and one of the lower right) in an
images with an overlapping region of 6 × 6. The Intersection over Union (IoU) between the two
boxes is (choose the closest value):
6406532878521.
21%
6406532878522.
25%
6406532878523.
33%
6406532878524.
37%
A published solution is not available for this question yet.
A four-dimensional input vector x = [5, 3,−1, 2] is passed to a hidden layer with a single neuron and
an activation function a(.) to obtain z. Assume that the corresponding weights (from input to
hidden layer) are [0.4, 0.6, 0.8,−0.2] and bias is 0.4. If the activation function a(.) is Sigmoid, Linear,
Indicator function, Softplus, ReLU and Leaky-ReLU, what are the corresponding values of z? (Note
that Indicator function returns 1 for a positive input, and 0 otherwise. Softplus is defined as: ln(1 +
exp(z)).
6406532878525.
0.95, 3, 1, 0.35, 3, 3
6406532878526.
0.95, 3, 0, 3.05, 3, 3
6406532878527.
0.92, 3, 1, 3.5, 3, 3
6406532878528.
0.95, 3, 1, 3.05, 3, 3
A published solution is not available for this question yet.
Consider a Faster R-CNN object detection framework, which is being trained with a mini-batch size
of 2. The RPN produces 512 proposals, out of which 12 and 14 of them are foreground
proposals,corresponding to each image in the mini-batch. For a single mini-batch update, the
bounding box regression loss will be computed_____________________ times.
A published solution is not available for this question yet.
A Siamese network is trained for face verification. The face image to be verified is passed through
the first branch and the anchor image is passed through the second branch. There are 73286
parameters in each of the branches. Triplet loss is used to learn the overall Siamese network. The
total number of trainable parameters in the network (assuming there are no other layers or
modules) are________________(write your answer as a number).
A published solution is not available for this question yet.
Consider generative and discriminative models for a classification task. Generative models learn
the data-generating mechanism by modeling class-conditional and prior distributions before
making predictions. Discriminative models make predictions based on patterns learned in the
training set. Which one of the following is an example of a generative model? Select all that are
correct.
6406532878492.
Convolutional Neural Network
6406532878493.
Naive-Bayes
6406532878494.
Logistic Regression
6406532878495.
Support Vector Machine
6406532878496.
Quadratic Discriminant Analysis
A published solution is not available for this question yet.
Which of the following is true regarding Hard Attention and Soft Attention?
6406532878533.
Soft Attention is smooth and differentiable
6406532878534.
Variance reduction techniques are used to train Soft Attention models
6406532878535.
Soft Attention is computationally cheaper than Hard Attention when the
source input is large
6406532878536.
The inference (test time) overhead is low in Hard Attention when compared to
Soft Attention models
**Algorithmic Thinking**
**Section Id :** 64065361114
**Section Number :** 8
**Section type :** Online
**Mandatory or Optional :** Mandatory
**Number of Questions :** 11
**Number of Questions to be attempted :** 11
**Section Marks :** 50
**Display Number Panel :** Yes
**Section Negative Marks :** 0
**Group All Questions :** No
**Enable Mark as Answered Mark for Review and**
No
**Clear Response :**
**Section Maximum Duration :** 0
**Section Minimum Duration :** 0
**Section Time In :** Minutes
**Maximum Instruction Time :** 0
A published solution is not available for this question yet.
