Question 83 MCQ · 3.0 marks
reduces
remains 90\(^{o}\)
increases
insufficient information
A published solution is not available for this question yet.
Deep Learning · End Term · Sep 2023 · AN
Deep Learning · End Term · Sep 2023 AN
← Course papers · Start practice / exam
Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.
0 / 18 published solutions
Question 84 MCQ · 1.0 marks
200
100
301
201
300
A published solution is not available for this question yet.
Question 85 MSQ · 3.0 marks
Increasing the value of b shifts the sigmoid function to the left (i.e., towards
negative infinity)
Increasing the value of b shifts the sigmoid function to the right (i.e., towards
positive infinity)
Increasing the value of w increases the steepness of the sigmoid function
Increasing the value of w decreases the steepness of the sigmoid function
A published solution is not available for this question yet.
Question 86 MSQ · 3.0 marks
Suppose that a neural network has millions of parameters (weights and biases). A team decides to
use an optimization algorithm with a learning rate scheme that is **local** to each parameter in the
network. Moreover, the learning rate changes in each iteration such that it should decrease on the
steep surface and increase on the gentle surface. Which of the following optimization algorithms
satisfy the team’s requirements?
GD with an exponentially decaying learning rate scheduler
AdaGrad
AdaM
NADAM
RMSProp
SGD with line search
A published solution is not available for this question yet.
Question 87 MSQ · 3.0 marks
Suppose we divide the available training samples into mini batches of size 32 to train a model with
mini-batch gradient descent. Assume that we have 33 different machines to train the model. One
out of 33 machines acts as a master machine. The actual weight update happens in the master
machine. The master machine can send one sample for the rest of the machines along with a copy
of the model in its current state to compute the gradients. We call this entire set-up parallelization.
Which of the following deep learning architectures can be trained in parallel then?
Fully connected Feed forword neural network
Convolutional Neural network
Reccurent Neural Network
Transformers
A published solution is not available for this question yet.
Question 88 MSQ · 2.0 marks
Select all correct statements about the bias and variance of deep learning models.
A model with high bias produces high training error and high validation error
A model with high variance produces high training error and low validation
error
A model with high variance produces low training error and high validation
error
Bias and variance can be both made zero if the underlying distribution of the
samples are known and also the samples are not corrupted by noise
A published solution is not available for this question yet.
Question 89 MSQ · 2.0 marks
Dropout reduces (removes) 25 percent of weights from the model during
training and inference
For each iteration, 75% of neurons are dropped randomly from the model
For each iteration, 25% of neurons are dropped randomly from the model
Each weight gets multiplied by a factor p during inference.
Each weight gets multiplied by a factor 1 − p during inference.
A published solution is not available for this question yet.
Question 90 MSQ · 5.0 marks
The loss surface is convex (with a global minimum)
The loss value oscillates over iterations
The loss value decreases consistently over iterations
The loss value increases consistently
A published solution is not available for this question yet.
Question 91 MSQ · 5.0 marks
definitely, the loss value at the end of the training is zero
The neuron in the hidden layer might be experiencing a vanishing gradient
problem
The loss could have converged to the local minimum after a finite number of
iterations
The loss value at the end of the training may not necessarily be zero
A published solution is not available for this question yet.
Question 92 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
How many neurons are there in the network? Every neuron in the network has bias associated
with it?
Note: A neuron is a computation unit that takes in some inputs and produces an output.
A published solution is not available for this question yet.
Question 93 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
How many parameters (including bias) does the network have to learn? Assume dropout
regularization is applied.
A published solution is not available for this question yet.
Question 94 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
What is the size of the vocabulary |V |?
A published solution is not available for this question yet.
Question 95 MCQ · 2.0 marks
Based on the above data, answer the given subquestions.
Suppose we consider the three words (wood,woodchuck, much). Assume we use one-hot encoded
vector representation for all these words. The statement that,“The cosine similarity between the
pair (wood,woodchuck) is greater than the pair (wood,much)” is
True
False
A published solution is not available for this question yet.
Question 96 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
How many parameters (including bias) are there in the network?
A published solution is not available for this question yet.
Question 97 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
For the given input sentence containing 10 words, how many sequential time steps does RNN take
to make a final prediction?
A published solution is not available for this question yet.
Question 98 NAT · 3.0 marks
Based on the above data, answer the given subquestions.
Suppose we train the model using the BPTT algorithm for 200 iterations. In each iteration, we feed
the input sentence and make a prediction, compute the loss, back-propagate through time and
update the parameter. How many times does the parameter matrix W get updated over 200
iterations?
A published solution is not available for this question yet.
Question 99 NAT · 3.0 marks
A published solution is not available for this question yet.
Question 100 NAT · 5.0 marks
A published solution is not available for this question yet.