cs3004_2023T3_Q1_NA.pdf

Deep Learning · Quiz 1 · Sep 2023

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

Question 40 SHORT_TEXT · 1.0 marks

Construct the savings tour using B as the base city. The savings for including the pairs of cities AC, AD and AE are 88, 48 and 61, respectively. Compute the savings for the remaining three pairs of cities, and use them to simulate the algorithm. Enter the path representation of the tour starting from city B. Enter a comma separated list of city names. NO SPACES, TABS, DOTS, BRACKETS, PARENTHESIS OR UNWANTED CHARACTERS. Answer format: B,X,Y,Z

A published solution is not available for this question yet.

Question 42 MSQ · 5.0 marks

Consider the two binary images shown below. The white square represents 0 and the black square represents 1. Suppose we use MP neuron to classify these two images by flattening the image of size 5 × 5 into a vector of length 25 × 1. [[IMAGE:59f6feccc5f0f8d4_3_0]] Which of the following threshold θ will help the MP neuron classify these two images correctly with the following decision rule? Assume the image of number two belongs to class (1) and the image of number one belongs to class (0) [[IMAGE:59f6feccc5f0f8d4_3_1]]

10
9
11
14
16
None of these

A published solution is not available for this question yet.

Question 43 NAT · 5.0 marks

[[IMAGE:59f6feccc5f0f8d4_4_2]] Based on the above data, answer the given subquestions.

[[IMAGE:59f6feccc5f0f8d4_5_3]]

A published solution is not available for this question yet.

Question 44 MCQ · 3.0 marks

[[IMAGE:59f6feccc5f0f8d4_4_2]] Based on the above data, answer the given subquestions.

The statement that the perceptron update rule works only for Boolean inputs and Boolean output is

TRUE
FALSE

A published solution is not available for this question yet.

Question 45 NAT · 5.0 marks

[[IMAGE:59f6feccc5f0f8d4_6_4]] Based on the above data, answer the given subquestions.

[[IMAGE:59f6feccc5f0f8d4_7_5]]

A published solution is not available for this question yet.

Question 46 MCQ · 5.0 marks

[[IMAGE:59f6feccc5f0f8d4_6_4]] Based on the above data, answer the given subquestions.

Suppose we run the model on the single input-output pair (x = 1, y = 0.062) for a few iterations by randomly initializing w and b. Moreover, the loss value is recorded for each iteration. We observe that the loss becomes zero after some iterations. This implies that the model has captured the true value of w and b that generated the pair x, y. The implication is

TRUE
FALSE

A published solution is not available for this question yet.

Question 47 MSQ · 3.0 marks

[[IMAGE:59f6feccc5f0f8d4_8_6]] Based on the above data, answer the given subquestions.

Choose the vector(s) which is (are) inappropriate given in the network

[[IMAGE:59f6feccc5f0f8d4_9_7]]
[[IMAGE:59f6feccc5f0f8d4_9_8]]
[[IMAGE:59f6feccc5f0f8d4_9_9]]
[[IMAGE:59f6feccc5f0f8d4_9_10]]

A published solution is not available for this question yet.

Question 48 NAT · 4.0 marks

[[IMAGE:59f6feccc5f0f8d4_8_6]] Based on the above data, answer the given subquestions.

Compute the vector **a3** and enter the sum of the elements of **a3**. If your answer is −1.2437, then enter it as −1.24. [[IMAGE:59f6feccc5f0f8d4_9_11]]

A published solution is not available for this question yet.

Question 49 MCQ · 3.0 marks

[[IMAGE:59f6feccc5f0f8d4_8_6]] Based on the above data, answer the given subquestions.

[[IMAGE:59f6feccc5f0f8d4_10_12]]

[[IMAGE:59f6feccc5f0f8d4_10_13]]
[[IMAGE:59f6feccc5f0f8d4_10_14]]
[[IMAGE:59f6feccc5f0f8d4_10_15]]
[[IMAGE:59f6feccc5f0f8d4_10_16]]

A published solution is not available for this question yet.

Question 50 NAT · 3.0 marks

[[IMAGE:59f6feccc5f0f8d4_8_6]] Based on the above data, answer the given subquestions.

[[IMAGE:59f6feccc5f0f8d4_10_17]]

A published solution is not available for this question yet.

Question 51 MCQ · 2.0 marks

[[IMAGE:59f6feccc5f0f8d4_8_6]] Based on the above data, answer the given subquestions.

[[IMAGE:59f6feccc5f0f8d4_11_18]]

0.41
-0.41
-11.11
-3.03

A published solution is not available for this question yet.

Question 52 NAT · 4.0 marks

[[IMAGE:59f6feccc5f0f8d4_8_6]] Based on the above data, answer the given subquestions.

[[IMAGE:59f6feccc5f0f8d4_11_19]]

A published solution is not available for this question yet.

Question 53 NAT · 5.0 marks

[[IMAGE:59f6feccc5f0f8d4_12_20]]

A published solution is not available for this question yet.

Question 54 MCQ · 3.0 marks

A team has a data set that contains 10000 samples for training a feed-forward neural network. Suppose they decided to use a mini-batch gradient descent algorithm with a batch size of 100 to update the weights. How many times do the weights get updated after training the network for 10 epochs?

1000
10000
100000
10 **Financial Forensics** **Section Id :** 64065345316 **Section Number :** 4 **Section type :** Online **Mandatory or Optional :** Mandatory **Number of Questions :** 12 **Number of Questions to be attempted :** 12 **Section Marks :** 25 **Display Number Panel :** Yes **Section Negative Marks :** 0 **Group All Questions :** No **Enable Mark as Answered Mark for Review and** Yes **Clear Response :** **Maximum Instruction Time :** 0

A published solution is not available for this question yet.