Question 75 MCQ · 2.0 marks
0
-6
6
7
-7
A published solution is not available for this question yet.
Deep Learning · End Term · May 2023 · FN
Deep Learning · End Term · May 2023 FN
← Course papers · Start practice / exam
This page contains the reliably extracted subset, not the complete original paper.
Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.
0 / 17 published solutions
Question 76 MCQ · 2.0 marks
Consider the statement “the attention mechanism in RNN based Encoder- Decoder architecture
helps the decoder to understand the context of words in a given sentence”. The statement is
True
False
A published solution is not available for this question yet.
Question 77 MSQ · 3.0 marks
A published solution is not available for this question yet.
Question 78 MSQ · 3.0 marks
Suppose that we have a deep Feed Forward Fully Connected Neural Network. The network is
observed to have a high variance. Then, which of the following techniques regularize the
parameter of the network to reduce the high variance ?
Adding L2 norm of weights to the loss function
Adding a noise to the input samples
Adding a noise to the output prediction
Adding more samples to the dataset by augmenting existing samples using
some augmentation techniques
Dropping hidden layers in a neural network randomly during training
A published solution is not available for this question yet.
Question 79 NAT · 3.0 marks
A published solution is not available for this question yet.
Question 80 NAT · 3.0 marks
A published solution is not available for this question yet.
Question 81 NAT · 3.0 marks
A published solution is not available for this question yet.
Question 82 NAT · 3.0 marks
Consider a simple RNN for a binary sequence classification problem.
A published solution is not available for this question yet.
Question 83 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 produce an output.
A published solution is not available for this question yet.
Question 84 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
How many learnable parameters (including bias) does the network have? Assume dropout
regularization is applied.
A published solution is not available for this question yet.
Question 85 MCQ · 1.0 marks
Based on the above data, answer the given subquestions.
For the given neural network configuration, we can replace the output layer with softmax
activation by logistic sigmoid and still use cross entropy loss. The statement is
True
False
A published solution is not available for this question yet.
Question 86 NAT · 2.0 marks
Consider a sentence inside the quote “I may be wrong, and you may be right, and by an effort, we
may get nearer to the truth”
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 87 NAT · 3.0 marks
Consider a sentence inside the quote “I may be wrong, and you may be right, and by an effort, we
may get nearer to the truth”
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 88 MCQ · 5.0 marks
A published solution is not available for this question yet.
Question 89 MCQ · 3.0 marks
True, due to the presence of noise in the target
True, due to the high variance of the prediction model
False, due to the high variance of the prediction model
False, due to zero mean of the noise added to the target
A published solution is not available for this question yet.
Question 90 MCQ · 5.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 91 MSQ · 5.0 marks
Based on the above data, answer the given subquestions.
**SPG**
**Section Id :** 64065341413
**Section Number :** 5
**Section type :** Online
**Mandatory or Optional :** Mandatory
**Number of Questions :** 33
**Number of Questions to be attempted :** 33
**Section Marks :** 40
**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.