cs3004_2025T2_ET_FN.pdf

Deep Learning · End Term · May 2025 FN

Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.

Question 98 MCQ · 2.0 marks

[[IMAGE:873d350454c40145_2_0]]

XOR
AND
OR
NAND
None of these

A published solution is not available for this question yet.

Question 99 MCQ · 2.0 marks

Based on the two statements provided choose the correct option? **Statement 1:** Optimization’s primary goal is to reduce the training error. **Statement 2:** Regularization helps to prevent overfitting, which in turn reduces the training error.

Both Statement 1 and Statement 2 are false.
Statement 1 is true, but Statement 2 is false.
Statement 1 is false, but Statement 2 is true.
Both Statement 1 and Statement 2 are true.

A published solution is not available for this question yet.

Question 100 MCQ · 2.0 marks

[[IMAGE:873d350454c40145_3_1]]

[[IMAGE:873d350454c40145_4_2]]
[[IMAGE:873d350454c40145_4_3]]
[[IMAGE:873d350454c40145_4_4]]
[[IMAGE:873d350454c40145_4_5]]

A published solution is not available for this question yet.

Question 101 MSQ · 3.0 marks

[[IMAGE:873d350454c40145_4_6]]

[[IMAGE:873d350454c40145_5_7]]
[[IMAGE:873d350454c40145_5_8]]
[[IMAGE:873d350454c40145_5_9]]
[[IMAGE:873d350454c40145_5_10]]
[[IMAGE:873d350454c40145_5_11]]
[[IMAGE:873d350454c40145_5_12]]

A published solution is not available for this question yet.

Question 102 NAT · 3.0 marks

[[IMAGE:873d350454c40145_5_13]] Based on the above data, answer the given subquestions.

[[IMAGE:873d350454c40145_6_14]]

A published solution is not available for this question yet.

Question 103 NAT · 3.0 marks

[[IMAGE:873d350454c40145_5_13]] Based on the above data, answer the given subquestions.

[[IMAGE:873d350454c40145_6_15]]

A published solution is not available for this question yet.

Question 104 NAT · 2.0 marks

[[IMAGE:873d350454c40145_5_13]] Based on the above data, answer the given subquestions.

[[IMAGE:873d350454c40145_7_16]]

A published solution is not available for this question yet.

Question 105 MCQ · 2.0 marks

[[IMAGE:873d350454c40145_7_17]] Based on the above data, answer the given subquestions.

What is the output of the convolution layer after applying ReLU?

[[IMAGE:873d350454c40145_8_18]]
[[IMAGE:873d350454c40145_8_19]]
[[IMAGE:873d350454c40145_8_20]]
[[IMAGE:873d350454c40145_8_21]]

A published solution is not available for this question yet.

Question 106 NAT · 1.0 marks

[[IMAGE:873d350454c40145_7_17]] Based on the above data, answer the given subquestions.

[[IMAGE:873d350454c40145_8_22]]

A published solution is not available for this question yet.

Question 107 NAT · 2.0 marks

[[IMAGE:873d350454c40145_7_17]] Based on the above data, answer the given subquestions.

[[IMAGE:873d350454c40145_8_23]]

A published solution is not available for this question yet.

Question 108 NAT · 2.0 marks

[[IMAGE:873d350454c40145_9_24]] Based on the above data, answer the given subquestions.

[[IMAGE:873d350454c40145_9_25]]

A published solution is not available for this question yet.

Question 109 MCQ · 2.0 marks

[[IMAGE:873d350454c40145_9_24]] Based on the above data, answer the given subquestions.

The CBOW model is now used to generate a “sentence” or a string of words. First we pass the word “good” and retain the word with highest probability as the output, say word1, which is in turn passed as input to the model. If the model is run this way for exactly three time steps, what is the sentence that it outputs? Note that the sentence here is “word1 word2 word3”. [[IMAGE:873d350454c40145_10_26]]

bad ugly good
good bad ugly
bad bad bad
good good good
bad ugly bad

A published solution is not available for this question yet.

Question 110 MCQ · 3.0 marks

[[IMAGE:873d350454c40145_9_24]] Based on the above data, answer the given subquestions.

Now consider updating the word embeddings using the sample “good good”. The first “good” in the string is used as context and the second “good” as the true label. Use cross entropy as the loss function and run one iteration of gradient descent with η = 1 starting with the existing values for the embeddings. Find the updated word embedding for “good” and choose the most appropriate option from below. Note that you have to compute the updated word embedding for “good” and not its context embedding.

(1.76, -0.24)
(1.24, -0.76)
(1.76, 1.76)
(1.76, -1.76)
(1.24, -1.24)

A published solution is not available for this question yet.

Question 111 NAT · 1.0 marks

[[IMAGE:873d350454c40145_12_27]] Based on the above data, answer the given subquestions.

Find s1.

A published solution is not available for this question yet.

Question 112 NAT · 2.0 marks

[[IMAGE:873d350454c40145_12_27]] Based on the above data, answer the given subquestions.

Find s2.

A published solution is not available for this question yet.

Question 113 NAT · 1.0 marks

[[IMAGE:873d350454c40145_12_27]] Based on the above data, answer the given subquestions.

[[IMAGE:873d350454c40145_13_28]]

A published solution is not available for this question yet.

Question 114 NAT · 3.0 marks

[[IMAGE:873d350454c40145_12_27]] Based on the above data, answer the given subquestions.

[[IMAGE:873d350454c40145_13_29]]

A published solution is not available for this question yet.

Question 115 NAT · 2.0 marks

[[IMAGE:873d350454c40145_14_30]] Based on the above data, answer the given subquestions.

[[IMAGE:873d350454c40145_14_31]]

A published solution is not available for this question yet.