cs3004_2025T1_Q1_NA.pdf
Deep Learning · Quiz 1 · Jan 2025
← 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.
Question 60 MCQ · 3.0 marks
Which of the following statements correctly distinguishes between Momentum Optimizer and
Nesterov Accelerated Momentum (NAG) Optimizer?
Momentum uses the current gradient to update the velocity, while NAG uses a
lookahead gradient based on a tentative future position.
Momentum is computationally faster than NAG because it skips calculating the
gradient at a lookahead position.
NAG is a variant of momentum that adjusts the step size dynamically during
training.
Momentum uses an adaptive learning rate, whereas NAG uses a fixed learning
rate.
A published solution is not available for this question yet.
Question 61 MCQ · 3.0 marks
Which of the functions given below has the steepest slope at the point x = 1?
[[IMAGE:b973cced2dbcdb1a_2_0]]

[[IMAGE:b973cced2dbcdb1a_2_1]]

[[IMAGE:b973cced2dbcdb1a_2_2]]

[[IMAGE:b973cced2dbcdb1a_2_3]]

A published solution is not available for this question yet.
Question 62 MSQ · 3.0 marks
[[IMAGE:b973cced2dbcdb1a_3_4]]

The weight update is tiny at a gentle loss surface.
The weight update is tiny at a steep loss surface.
The weight update is large at a steep loss surface.
The weight update is large at a gentle loss surface.
A published solution is not available for this question yet.
Question 63 NAT · 3.0 marks
Consider a network trained on a dataset of 5000 data-points using mini-batch gradient descent
with a batch size of 50. If the network is trained for 100 epochs, how many times does each
parameter in the network get updated?
A published solution is not available for this question yet.
Question 64 NAT · 2.0 marks
Consider a perceptron for a binary classification task. There are four features each of which is
binary. The dataset has 16 data-points. The feature vector for no two data-points is the same. The
weight vector is **w** = (1, 1,−1,−1). Ignore the bias.
[[IMAGE:b973cced2dbcdb1a_4_5]]
If the number of misclassifications is zero on this dataset, answer the given subquestions.
Find the number of data-points in the dataset that have true label 1.

A published solution is not available for this question yet.
Question 65 NAT · 2.0 marks
Consider a perceptron for a binary classification task. There are four features each of which is
binary. The dataset has 16 data-points. The feature vector for no two data-points is the same. The
weight vector is **w** = (1, 1,−1,−1). Ignore the bias.
[[IMAGE:b973cced2dbcdb1a_4_5]]
If the number of misclassifications is zero on this dataset, answer the given subquestions.
Find the number of data-points in the dataset that have true label 0.

A published solution is not available for this question yet.
Question 66 MCQ · 2.0 marks
[[IMAGE:b973cced2dbcdb1a_5_6]]
Based on the above data, answer the given subquestions.
[[IMAGE:b973cced2dbcdb1a_5_7]]


(−0.8, 0.8)
(0.08,−0.08)
(−0.08, 0.08)
(1,−1)
A published solution is not available for this question yet.
Question 67 NAT · 2.0 marks
[[IMAGE:b973cced2dbcdb1a_5_6]]
Based on the above data, answer the given subquestions.
[[IMAGE:b973cced2dbcdb1a_5_8]]


A published solution is not available for this question yet.
Question 68 MSQ · 2.0 marks
[[IMAGE:b973cced2dbcdb1a_6_9]]
Based on the above data, answer the given subquestions.
[[IMAGE:b973cced2dbcdb1a_6_10]]


(0, 0)
(0, 1)
(−1, 1)
(1, 1)
A published solution is not available for this question yet.
Question 69 NAT · 2.0 marks
[[IMAGE:b973cced2dbcdb1a_6_9]]
Based on the above data, answer the given subquestions.
What is the value of k?

A published solution is not available for this question yet.
Question 70 MSQ · 2.0 marks
[[IMAGE:b973cced2dbcdb1a_6_9]]
Based on the above data, answer the given subquestions.
[[IMAGE:b973cced2dbcdb1a_7_11]]


[[IMAGE:b973cced2dbcdb1a_7_12]]

[[IMAGE:b973cced2dbcdb1a_7_13]]

[[IMAGE:b973cced2dbcdb1a_7_14]]

[[IMAGE:b973cced2dbcdb1a_7_15]]

A published solution is not available for this question yet.
Question 71 NAT · 1.0 marks
[[IMAGE:b973cced2dbcdb1a_7_16]]
Based on the above data, answer the given subquestions.
Calculate the value of z (correct up to two decimal places).

A published solution is not available for this question yet.
Question 72 NAT · 1.0 marks
[[IMAGE:b973cced2dbcdb1a_7_16]]
Based on the above data, answer the given subquestions.
[[IMAGE:b973cced2dbcdb1a_8_17]]


A published solution is not available for this question yet.
Question 73 NAT · 1.0 marks
[[IMAGE:b973cced2dbcdb1a_7_16]]
Based on the above data, answer the given subquestions.
[[IMAGE:b973cced2dbcdb1a_8_18]]


A published solution is not available for this question yet.
Question 74 NAT · 3.0 marks
[[IMAGE:b973cced2dbcdb1a_7_16]]
Based on the above data, answer the given subquestions.
[[IMAGE:b973cced2dbcdb1a_9_19]]


A published solution is not available for this question yet.
Question 75 NAT · 1.0 marks
[[IMAGE:b973cced2dbcdb1a_10_20]]
Based on the above data, answer the given subquestions.
What is the value of the output of the first sigmoid neuron in the first hidden layer (i.e. h11).
(Answer correct upto two digits after the decimal)

A published solution is not available for this question yet.
Question 76 NAT · 1.0 marks
[[IMAGE:b973cced2dbcdb1a_10_20]]
Based on the above data, answer the given subquestions.
What is the value of the output of the first sigmoid neuron in the second hidden layer (i.e. h21)
(Answer correct upto two digits after the decimal)

A published solution is not available for this question yet.
Question 77 NAT · 1.0 marks
[[IMAGE:b973cced2dbcdb1a_10_20]]
Based on the above data, answer the given subquestions.
What is the value of the output of the first neuron in the third or output layer with the softmax
activation function (i.e. h31) (Answer correct upto two digits after the decimal)

A published solution is not available for this question yet.
Question 78 NAT · 1.0 marks
[[IMAGE:b973cced2dbcdb1a_10_20]]
Based on the above data, answer the given subquestions.
What is the value of the cross entropy loss? (use natural log). (Answer correct upto two digits after
the decimal)

A published solution is not available for this question yet.
Question 79 NAT · 2.0 marks
[[IMAGE:b973cced2dbcdb1a_10_20]]
Based on the above data, answer the given subquestions.
[[IMAGE:b973cced2dbcdb1a_12_21]]


A published solution is not available for this question yet.
Question 80 NAT · 2.0 marks
[[IMAGE:b973cced2dbcdb1a_10_20]]
Based on the above data, answer the given subquestions.
[[IMAGE:b973cced2dbcdb1a_12_22]]


A published solution is not available for this question yet.