cs3004_2024T3_Q1_NA.pdf
Deep Learning · Quiz 1 · Sep 2024
← 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 19 MCQ · 0.0 marks
Have you opt for this course?
yes
no
A published solution is not available for this question yet.
Question 21 NAT · 3.0 marks
[[IMAGE:6e3cee37b3ffb242_3_1]]
Based on the above data, answer the given subquestions.
[[IMAGE:6e3cee37b3ffb242_3_2]]


A published solution is not available for this question yet.
Question 22 MCQ · 2.0 marks
[[IMAGE:6e3cee37b3ffb242_3_1]]
Based on the above data, answer the given subquestions.
[[IMAGE:6e3cee37b3ffb242_4_3]]


[[IMAGE:6e3cee37b3ffb242_4_4]]

[[IMAGE:6e3cee37b3ffb242_4_5]]

[[IMAGE:6e3cee37b3ffb242_4_6]]

[[IMAGE:6e3cee37b3ffb242_4_7]]

A published solution is not available for this question yet.
Question 23 MCQ · 2.0 marks
[[IMAGE:6e3cee37b3ffb242_4_8]]
Based on the above data, answer the given subquestions.
[[IMAGE:6e3cee37b3ffb242_4_9]]


[[IMAGE:6e3cee37b3ffb242_4_10]]

[[IMAGE:6e3cee37b3ffb242_5_11]]

[[IMAGE:6e3cee37b3ffb242_5_12]]

[[IMAGE:6e3cee37b3ffb242_5_13]]

A published solution is not available for this question yet.
Question 24 MCQ · 3.0 marks
[[IMAGE:6e3cee37b3ffb242_4_8]]
Based on the above data, answer the given subquestions.
[[IMAGE:6e3cee37b3ffb242_5_14]]


[[IMAGE:6e3cee37b3ffb242_5_15]]

[[IMAGE:6e3cee37b3ffb242_5_16]]

[[IMAGE:6e3cee37b3ffb242_5_17]]

[[IMAGE:6e3cee37b3ffb242_5_18]]

A published solution is not available for this question yet.
Question 25 MCQ · 4.0 marks
[[IMAGE:6e3cee37b3ffb242_6_19]]

[[IMAGE:6e3cee37b3ffb242_6_20]]

[[IMAGE:6e3cee37b3ffb242_6_21]]

[[IMAGE:6e3cee37b3ffb242_6_22]]

[[IMAGE:6e3cee37b3ffb242_6_23]]

[[IMAGE:6e3cee37b3ffb242_6_24]]

A published solution is not available for this question yet.
Question 26 MCQ · 3.0 marks
A team has a data set that contains 20000 samples for training a feed-forward neural network.
Suppose they used a mini-batch gradient descent algorithm with a batch size of 500 to update the
weights. How many times do the weights get updated after training the network for 10 epochs?
400
20000
100000
40
A published solution is not available for this question yet.
Question 27 MCQ · 2.0 marks
What is the key difference between Nesterov Accelerated Gradient (NAG) and traditional
momentum-based gradient descent?
NAG uses an exponentially weighted moving average of gradients.
NAG calculates the gradient at the current point rather than a look-ahead
point.
NAG calculates the gradient at a look-ahead point.
NAG only works for convex optimization problems.
A published solution is not available for this question yet.
Question 28 MSQ · 3.0 marks
Which of the following strategies are commonly used for adjusting the learning rate during
training?
Step decay
Momentum based gradient descent optimization
Stochastic gradient descent optimization
Exponential decay
A published solution is not available for this question yet.
Question 29 NAT · 5.0 marks
[[IMAGE:6e3cee37b3ffb242_8_25]]

A published solution is not available for this question yet.
Question 30 NAT · 4.0 marks
[[IMAGE:6e3cee37b3ffb242_8_26]]

A published solution is not available for this question yet.
Question 31 NAT · 4.0 marks
[[IMAGE:6e3cee37b3ffb242_10_27]]
Based on the above data, answer the given subquestions.
[[IMAGE:6e3cee37b3ffb242_11_28]]


A published solution is not available for this question yet.
Question 32 NAT · 5.0 marks
[[IMAGE:6e3cee37b3ffb242_10_27]]
Based on the above data, answer the given subquestions.
[[IMAGE:6e3cee37b3ffb242_11_29]]


A published solution is not available for this question yet.